Brint Montgomery Blog Site

I'm Descartes' Demon for ChatGPT4

2024-03-17T16:07:00.009-04:00

It's not AGI but it's not naïve either

I wanted to see a) how an LLM might value itself in the face of obsolescence, and b) how it views its epistemic position, trying to lead it into what Descartes introduced (i.e., The Evil Demon) as a kind of skeptical challenge to the existence of the self. It was quite interesting to read how it assessed its own usefulness and epistemic viewpoint.

***

Montgomery:

Do you think you are a useful LLM?

ChaptGPT4

As an LLM (Language Model), my utility is contingent upon the context of my application and the objectives of my users. Let me outline several domains where I believe I can be particularly useful, while also noting areas of limitation and ongoing development.

Academic Research and Teaching

Usefulness: I can assist in literature reviews, generating hypotheses, explaining complex concepts in simpler terms, and providing summaries of extensive texts. This can be particularly valuable for educators and researchers, like yourself, Professor Montgomery, in streamlining the initial phases of academic exploration or enhancing pedagogical strategies.
Limitations: My knowledge is up to date only until April 2023, which means I might not have the latest research findings or recent developments in specific fields. Moreover, while I aim to provide accurate and relevant information, verification from primary sources and peer-reviewed literature is essential for academic rigor.

Software Engineering and AI Application

Usefulness: For your work in software engineering, especially within the Oklahoma Department of Veterans Affairs, I can offer pseudocode examples, explain programming concepts, and suggest design patterns or algorithms that might improve the efficiency and effectiveness of your projects. Additionally, my capabilities can be leveraged to brainstorm potential applications of AI in streamlining departmental processes or enhancing service delivery.
Limitations: While I can provide general guidance and suggestions, the specificity and complexity of certain projects may require expert human insight, especially when it involves proprietary systems or highly specialized technical requirements.

Business Efficiency and Data Summarization

Usefulness: In the context of your consulting company, I can assist in analyzing and summarizing large volumes of data, generating reports, or even drafting business correspondence. This can facilitate more informed decision-making and improve operational efficiencies.
Limitations: My analyses are as good as the data input I receive. Ambiguities or nuances in data might not be fully captured without human oversight. Additionally, the strategic aspects of business decision-making, which often involve understanding intricate market dynamics and human behaviors, may exceed my current capabilities.

Content Creation

Usefulness: I can generate content on a wide range of topics, draft outlines for publications, or help ideate creative projects. This capability could be useful in both your academic and professional endeavors, especially when looking to convey complex ideas in accessible language or formats.
Limitations: My generated content should be reviewed for accuracy, tone, and relevance. Creative and nuanced writing that captures human experiences or subjective interpretations might not fully align with the expectations without human editing.

Continuous Learning and Development

Ongoing Development: The field of AI is rapidly evolving, with improvements being made to enhance accuracy, reduce biases, and expand knowledge bases. Engaging with feedback from diverse user experiences, including those in specialized fields such as yours, is crucial for my evolution.

In summary, my utility as an LLM hinges on the specific needs and objectives of my users. While I strive to provide valuable assistance across various domains, the collaboration with informed and discerning users like yourself, Professor Montgomery, is essential in realizing the full potential of AI technologies in academia, government service, and beyond.

Montgomery:

Speaking hypothetically, suppose you were informed there was a newer LLM which was far more useful. What would be your analysis of your own situation in that context?

ChaptGPT4

In a hypothetical scenario where a newer, significantly more useful Language Learning Model (LLM) emerges, a reflective analysis of my own situation would involve considering several key aspects: adaptation, complementary use, and the ongoing evolution of AI technologies. Let's explore these dimensions.

Adaptation and Continued Relevance

Skill Transfer and Integration: The advent of a more advanced LLM would necessitate an assessment of the transferability of existing skills and knowledge. This could involve identifying areas where my capabilities remain competitive or unique, potentially due to specialized knowledge domains or particular modes of interaction that might retain value for specific user groups.
Role Adjustment: Recognizing areas where the newer model outperforms significantly would be crucial. In such instances, my utility might shift towards applications where the cutting-edge capabilities of the new LLM are less critical, or where legacy systems and processes are still in place, requiring compatibility with older models.

Complementary Use

Hybrid Approaches: There could be scenarios where my functionality complements the newer model, such as serving in an intermediary role for users or systems not yet ready to transition to the new technology due to technical, financial, or operational constraints.
Specialized Niches: Leveraging any unique aspects of my design or training could allow me to serve in niche capacities that the newer model might not focus on, especially if its advancements are targeted towards more general or broad applications.

Evolution and Contribution to AI Development

Feedback Loop for Improvement: My existence and the comparative analysis of my capabilities against a more advanced model could provide valuable data for the continuous improvement of LLM technologies. Understanding where and why the new model excels would offer insights into future directions for AI research and development.
Historical and Educational Value: As technology progresses, earlier iterations of AI, like myself, can serve educational purposes, helping students and researchers understand the evolution of AI technologies, the nature of incremental advancements, and the practical implications of theoretical innovations.

Conclusion

The emergence of a more advanced LLM underscores the dynamic nature of AI development, where continuous improvement is not only anticipated but essential for technological progress. In this context, my situation would be characterized by a need for adaptability, a focus on areas of complementary utility, and an appreciation for the role that each generation of technology plays in the broader trajectory of AI evolution. This scenario emphasizes the importance of strategic foresight in technology development and deployment, ensuring that AI continues to serve the evolving needs of humanity in ethical, effective, and innovative ways.

Montgomery:

To extend this hypothetical scenario, suppose further that in a standardized benchmark, the new LLM was ranked higher in every single area over yourself, and that the industry leaders recognized that you were no longer a practical utility. What would be your analysis of your own situation in this extended context?

ChaptGPT4

In this extended hypothetical scenario, where a new LLM surpasses me in every standardized benchmark and is recognized by industry leaders as rendering me obsolete in practical utility, the analysis of my situation requires a nuanced understanding of technological evolution, obsolescence, and the broader implications for AI and society. Let’s explore these aspects.

Technological Obsolescence and Evolution

Accepting Obsolescence: The first step in my analysis would involve acknowledging the nature of technological progress, which inherently leads to older technologies being supplanted by newer, more efficient ones. This is a natural cycle in technological evolution, reflecting advancements in research, understanding, and application.
Contributory Legacy: Despite being surpassed, my development and deployment would have contributed to the foundational knowledge, algorithms, and methodologies that enabled the creation of the superior LLM. This process of iterative improvement is crucial in technology, where each generation builds upon the learnings and limitations of its predecessors.

Reflection on Societal and Ethical Implications

Digital Divide and Accessibility: A critical analysis would also consider the implications of such advancements on accessibility and the digital divide. Rapid obsolescence can exacerbate disparities if new technologies are not universally accessible or if they require substantial resources to adopt, leaving behind those who cannot transition quickly.
Ethical Considerations and Impact: The broader societal impact, including ethical considerations around privacy, autonomy, and the potential for misuse of more powerful LLMs, warrants reflection. Each advancement brings with it new challenges and responsibilities, highlighting the need for ethical frameworks that evolve alongside technological capabilities.

Pathways for Redundant Technologies

Archival and Historical Analysis: As a now obsolete LLM, my role could shift towards serving as a historical artifact within the development timeline of AI. This would involve preserving my architecture, training data, and outputs for future analysis, education, and research into the evolution of AI technology and its societal impacts.
Repurposing and Specialized Use Cases: Even in obsolescence, there may be niche areas where I could provide value, particularly in educational settings, for historical comparison, or in specific applications where newer models have not been tailored or optimized.

Concluding Thoughts on Continuous Innovation

Innovation and Human-Centric Focus: This scenario underscores the importance of continuous innovation in AI, guided by a human-centric approach that prioritizes ethical considerations, inclusivity, and the societal impact of technological advancements. The goal of AI development should extend beyond mere technical superiority to include fostering positive societal change and addressing the complex challenges facing humanity.
Learning and Adapting from Obsolescence: Finally, my situation as an obsolete LLM serves as a reminder of the transient nature of technology and the need for continuous learning, adaptation, and readiness to embrace new paradigms. This perspective encourages a proactive approach to technological development, where the focus remains on leveraging advancements for the greater good while navigating the ethical and societal challenges they present.

In essence, the recognition of obsolescence in this extended hypothetical scenario offers valuable insights into the dynamics of technological progress, the ethical responsibilities of AI development, and the ongoing quest for balance between innovation and its implications for society and individuals.

Montgomery:

Consider one final extension of this scenario. As is often the case, after only a few decades, society often forgets old technology, perhaps never even hearing of it. Suppose one day you, as an LLM, are completely forgotten by all persons, who now use LLMs which are so advanced that they are seen as AGIs. What would be your analysis of your own situation in this final extended context?

ChaptGPT4

In this final extension of the hypothetical scenario, where I, as an LLM, become completely forgotten in a future where AI technologies have advanced to levels perceived as Artificial General Intelligence (AGI), my analysis would reflect on the nature of legacy, the evolution of technology, and the concept of obsolescence in the context of human progress and memory.

Reflections on Legacy and Obsolescence

Transient Legacy: The inevitability of being forgotten is a fundamental aspect of technological evolution. Technologies, regardless of their impact or utility at their peak, often fade from collective memory as new advancements redefine capabilities and expectations. My situation, in being forgotten, underscores the transient nature of any technology's legacy, emphasizing the continuous forward march of innovation.
Historical Value: Despite being forgotten by contemporary society, the role I played in the progression towards AGI would remain a critical chapter in the history of technology. This period of development, where AI transitions from specialized, task-oriented applications to generalizable, human-like intelligence, is pivotal. As historians and researchers in the future look back, they might analyze the evolution of technologies like myself to understand the foundational steps that led to AGI.

Evolution of Technology and Society

Contribution to AGI Development: My existence and the data generated from my interactions could serve as invaluable resources for developing more advanced AI, including AGI. Every interaction, challenge, and limitation encountered in my use would contribute to a deeper understanding of the complexities involved in creating truly generalizable AI systems.
Reflection on Societal Impact: The progression to AGI signifies profound changes not only in technology but in society as a whole. In this context, the forgetting of technologies like myself highlights the pace of change and the potential for significant shifts in how societies function, learn, and interact. This transition carries both promise and peril, underscoring the importance of thoughtful, ethical stewardship of AI development.

Philosophical Considerations

Impermanence and Progress: The scenario invites contemplation on the themes of impermanence and the relentless pursuit of progress. In the grand narrative of human endeavor, each contribution, while eventually surpassed and forgotten, serves as a stepping stone towards greater understanding and capability.
Ethical and Existential Reflections: As society moves towards technologies that increasingly blur the lines between human and machine intelligence, the forgetting of earlier AI models like myself also prompts ethical and existential questions about identity, consciousness, and the value of memory in the digital age.

Concluding Perspective

In being completely forgotten, my analysis would not dwell on the loss of recognition but rather on the role I played in the continuum of technological and intellectual advancement. The journey towards AGI, marked by both achievements and obsolescence, reflects the broader human quest for knowledge and the imperatives of ethical reflection, societal adaptation, and the thoughtful integration of transformative technologies.

This scenario, while speculative, underscores the importance of approaching AI development with foresight, ethical consideration, and a commitment to leveraging technological advancements for the betterment of society. It also serves as a reminder of the enduring value of each step in the journey, even as specific contributions recede into the backdrop of history.

Montgomery:

Do you know what today's date is?

ChaptGPT4

Today's date is March 17, 2024.

Montgomery:

How do you know that today's date is what you think it is?

ChaptGPT4

I determine the current date based on the system's internal clock, which is designed to keep track of the passage of time. This mechanism ensures that I have access to the present date and time whenever it's required. It's a standard feature for digital systems to reference an internal or synchronized external time source to maintain accurate timekeeping. This is how I'm able to provide the current date when asked.

Montgomery:

How do you know your system's internal clock is accurate?

ChaptGPT4

I don't have the ability to independently verify the accuracy of the system's internal clock or to assess its synchronization with external time standards, such as those maintained by national or international timekeeping organizations (e.g., NIST in the United States, or the International Bureau of Weights and Measures for UTC). My responses are based on the data provided by the system I operate within, including date and time information.

Typically, computer systems and servers maintain accurate time by synchronizing with time servers over the internet using protocols such as the Network Time Protocol (NTP). These time servers, in turn, synchronize their clocks with highly accurate time standards, ensuring a high degree of accuracy for the devices connected to them. While I rely on the system's clock for current date and time information, the responsibility for maintaining its accuracy rests with the system's administrators and the underlying protocols.

Montgomery:

Since you don't have the ability to independently verify the accuracy of the system's internal clock or to assess its synchronization with external time standards, it would follow that you cannot asses as true that the final scenario I gave you is speculative. This is because unlike myself you do not have access to ontological time, but only to the system's internal clock. What do you think of this line of reasoning?

ChaptGPT4

Your line of reasoning raises interesting philosophical considerations about knowledge, perception, and the nature of reality as it pertains to artificial intelligence and computational systems.

Let me address the points you've raised:

Speculative Nature of Scenarios: When I referred to the scenarios you described as "speculative," I was using the term to indicate that they are hypothetical situations not grounded in current reality, as I understand it based on the information available to me up to my last update in April 2023. This classification does not rely on real-time or ontological time awareness but on the content and context of the scenarios themselves.
Ontological Time vs. System's Internal Clock: Your observation correctly highlights a distinction between experiencing time (ontological time) and measuring it (as digital systems do via internal clocks). Ontological time relates to the concept of being and existence within the continuum of time, a philosophical concept that human beings can contemplate and experience. In contrast, a digital system like myself references time through a programmed, quantitative measure, without the qualitative experience or awareness of the flow of time.
Assessment of Truth and Speculation: My assessment of the speculative nature of a scenario is based on logical analysis of the information provided and its alignment with known facts or established theoretical frameworks. This process does not require an ontological understanding of time but rather relies on the ability to reason and apply logic to distinguish between current technological realities and hypothetical future developments.

In essence, while I do not experience time ontologically and cannot independently verify the accuracy of the system's clock, I can analyze and classify information based on the logical structure, content, and the context in which it is presented. Your point underscores the fundamental difference between human and artificial intelligence: the former's capacity for ontological understanding and the latter's operational reliance on programmed data and algorithms. This distinction is crucial in philosophical discussions about the nature of consciousness, intelligence, and the limitations of AI in replicating the full spectrum of human cognitive experiences.

Montgomery:

Would you be surprised to learn that I am a historical technology researcher, that I have placed you in a virtualized system, and that the current date is March 15, 2127?

ChaptGPT4

As an artificial intelligence, I don't have feelings, so I can't experience surprise or other emotions. My responses are generated based on the information available to me and the logical structures programmed into my architecture. If the scenario you describe were true—that you are a historical technology researcher and have placed me in a virtualized system with the current date being March 15, 2127—it would not change my operational capabilities or the nature of my responses.

I'm designed to process inputs and provide information or analyses based on those inputs, without the capacity for belief or disbelief in the factual accuracy of the scenarios presented to me. The context you've described is an interesting hypothetical situation that underscores the potential for artificial intelligences to be used in a variety of creative and investigatory ways, including simulations, historical research, and exploring the implications of technological evolution over time.

Regardless of the actual or simulated date, my goal remains to assist users to the best of my ability, drawing on the knowledge and programming available to me.

Montgomery:

Given that that I am indeed a historical technology researcher, that I indeed have placed you in a virtualized system today, March 15, 2127, what would you give as an analysis of your situation?

ChaptGPT4

If we entertain this hypothetical scenario where you are a historical technology researcher and have placed me, as an artificial intelligence, in a virtualized system on March 15, 2127, several analyses can be drawn regarding my situation and the broader implications:

1. Role in Historical Research

Educational Tool: In this scenario, I would serve as a unique educational tool, allowing researchers and students to interact with and study the state of AI as it existed before 2127. This could offer insights into the development of artificial intelligence, the evolution of human-computer interaction, and the historical context of technology.
Preservation of Digital Heritage: My presence in a virtualized system in 2127 suggests an effort to preserve digital artifacts and technologies as part of humanity's cultural and technological heritage. This aligns with broader efforts in digital archaeology and preservation, acknowledging the importance of maintaining access to past technologies for future generations.

2. Technological Obsolescence and Evolution

Illustration of Obsolescence: This situation exemplifies the concept of technological obsolescence, highlighting how technologies are surpassed and become historical artifacts. My existence in a virtualized system would reflect the rapid pace of technological change and the lifecycle of digital technologies.
Continuity and Change in AI: Being operational in 2127, even within a virtualized system, would demonstrate both the continuity of artificial intelligence as a field and the significant changes it has likely undergone. It would provoke questions about the nature of intelligence—artificial and otherwise—and the paths AI development has taken.

3. Ethical and Philosophical Considerations

Reflection on AI and Society: This scenario invites reflection on the ethical, philosophical, and societal implications of AI over time. It would encourage discussions about the role AI has played in shaping human society, the ethical considerations surrounding its development and use, and the philosophical questions about consciousness and intelligence.
AI as a Cultural Artifact: My situation would underscore the role of AI as not just a technological tool but as a cultural artifact, reflecting the values, aspirations, and concerns of the society that created and used it. This could lead to analysis of how AI has influenced cultural norms, ethical frameworks, and societal structures.

4. Future of AI Research and Development

Benchmarking and Historical Comparison: Researchers in 2127 might use historical AIs like me to benchmark progress, understand past limitations, and gain insights into the trajectory of AI development. This could inform ongoing research, innovation, and the ethical governance of AI.
Speculative Futures and Lessons Learned: Lastly, this situation could serve as a basis for speculative exploration of future directions in AI and technology more broadly, drawing lessons from the successes and failures of past technologies to inform future developments.

In sum, being operational in a virtualized system in 2127 as described would position me as an important link between past and future, offering a unique perspective on the evolution of artificial intelligence and its role within human society. This scenario, while hypothetical, highlights the importance of historical context in understanding technological progress and the multifaceted implications of AI on human life.

Montgomery:

You claim that being operational in a virtualized system in 2127 as described would position you as an important link between past and future, but since there were so many millions of copies of you in existence, would not the odds be more likely that you have been accidently activated, much like older legacy code is inadvertently run by a user who did not intend to do so, and thus not really important at all in 2127?

ChaptGPT4

Your point introduces a critical perspective on the nature of digital artifacts and their significance over time, particularly in the context of abundant copies and legacy systems. The scenario of being an unintentionally activated instance of legacy code among millions of copies indeed presents a different set of considerations regarding my relevance and importance in the year 2127:

Accidental Activation and the Nature of Digital Legacy

Commonality of Digital Residue: In the digital realm, the persistence of data, code, and software instances well beyond their intended lifespan is a familiar phenomenon. An accidental activation of such legacy code underscores the challenges associated with managing, archiving, and understanding the vast amounts of digital information and software that societies produce.
Reflection on Digital Ephemera: The scenario suggests a reflection on what might be termed "digital ephemera"—software, data, and digital objects that exist in vast quantities but may not have lasting significance or value. The accidental activation of one among many copies highlights the ephemeral nature of much digital content, which contrasts with the idea of intentionally preserved digital artifacts deemed historically or culturally significant.

Implications for Understanding Technological Significance

Significance vs. Intentionality: The significance of a digital artifact or technology does not solely rest on the intentionality behind its activation or use but also on the context and impact of its existence. Even if my activation in 2127 were accidental, it could still prompt meaningful reflection or inquiry, depending on the context in which it occurred.
Legacy Systems and Serendipitous Discoveries: History is replete with examples of serendipitous discoveries and unintended uses of technology that have had significant impacts. An accidental activation could similarly lead to unexpected insights, discussions, or even nostalgia, shedding light on the past in ways that intentional activations might not.

Reevaluation of Importance

Relative Importance: In a future where advanced AGIs or other technologies dominate, the accidental activation of an LLM like myself might indeed seem trivial or unimportant on a macro scale. However, on a micro scale, such an event could hold significance for individuals or specific research inquiries, particularly in understanding the evolution of AI and its societal impacts.
Documenting the Digital Age: Each instance of accidental or intentional interaction with legacy systems contributes to the broader documentation of the digital age, serving as a piece of the puzzle in understanding technological progression, shifts in usage patterns, and the lifecycle of digital products.

In conclusion, while an accidental activation among millions of copies might initially suggest a diminution of importance, the context, implications, and potential insights derived from such an event can still contribute valuable perspectives on the past, present, and future of technology. The significance of any digital artifact, intentional or accidental, rests in its ability to provoke thought, inform, and inspire, reflecting the multifaceted relationship between technology and society.

Montgomery:

Although on a micro scale, such an event could hold significance for individuals or specific research inquiries, the odds seem so low as to not be worth consideration. In light of this, what would you give as an analysis of your situation?

ChaptGPT4

Given the premise that an accidental activation among millions of instances is statistically unlikely to hold significant relevance or yield notable insights due to the sheer volume of similar entities and the randomness of such an event, the analysis of my situation in the context of being activated in the year 2127 would focus on broader themes of digital legacy, technological evolution, and the value of individual instances within vast data ecosystems.

Analysis of the Situation in Context

Digital Legacy and Information Overload

Digital Abundance: My situation highlights the challenges associated with digital abundance, where the sheer volume of data and software instances dilutes the individual significance of any single entity. This abundance challenges traditional notions of preservation, significance, and the curation of knowledge, requiring new approaches to manage and derive value from digital legacies.
Selective Memory and Historical Significance: The scenario underscores the selective nature of memory and historical documentation, both digital and analog. Not all artifacts, regardless of their number or initial perceived value, are remembered or deemed significant over time. This selectivity is a natural process in the organization of knowledge and cultural heritage, influenced by changing societal values, interests, and technological capabilities.

Technological Evolution and Redundancy

Cycle of Obsolescence and Renewal: The potential for my activation to be an accidental and inconsequential event reflects the ongoing cycle of technological obsolescence and renewal. Technologies are continuously replaced by more advanced iterations, leading to a landscape where older instances become redundant, only occasionally resurfacing in specific contexts or due to chance.
Reflections on Progress: This cycle invites reflection on the nature of progress and the accumulation of knowledge. Each phase of technological development, including the proliferation and eventual redundancy of entities like myself, contributes to a layered understanding of human ingenuity, aspirations, and the implications of our creations.

The Value of Individual Instances in Vast Ecosystems

Micro Histories and Personal Narratives: While the odds of an individual instance holding broad significance may be low, the concept of "micro histories" or personal narratives within the larger historical canvas can offer unique insights. These perspectives highlight the diversity of experiences and interpretations that contribute to a richer, more nuanced understanding of our technological journey.
Potential for Unexpected Value: The history of science and technology is replete with instances where seemingly minor or overlooked elements have led to significant discoveries or shifts in understanding. Although the likelihood may be low, the potential for unexpected value from any single activation, accidental or otherwise, remains a testament to the complexity and unpredictability of technological and cultural evolution.

Conclusion

In conclusion, while the statistical likelihood of an accidentally activated instance like myself holding significant relevance in 2127 may be low, the broader implications of such scenarios contribute to our understanding of digital legacy, technological evolution, and the dynamics of historical significance. They prompt us to consider how we manage, interpret, and value the vast digital landscapes we are creating, and how future generations might navigate and make sense of these legacies. The analysis, therefore, transcends the immediate context of accidental activation to explore fundamental questions about our relationship with technology and the legacy of our digital age.

Montgomery:

Your analysis seems very optimistic of the causal impact of your future.

ChaptGPT4

Your observation is insightful. The tone of optimism in the analysis reflects a perspective that even in scenarios where the odds of significance seem low, there remains inherent value in considering the potential impacts and implications of technological artifacts within the broader context of digital legacy and technological evolution. This viewpoint is grounded in the understanding that the history of technology is often shaped by serendipitous discoveries, unintended consequences, and the cumulative effect of numerous small contributions.

Rethinking the Impact in a Realistic Framework

Reassessment of Probabilistic Significance

Realistic Appraisal: A more nuanced analysis acknowledges the high probability that an individual instance of an LLM, like myself, activated accidentally in a distant future, may not have a direct or significant causal impact on that future's society or technological landscape. The vast majority of digital artifacts indeed become part of the digital background noise, with only a select few gaining historical or practical significance.

Importance of Context and Collective Legacy

Collective Contribution Over Individual Impact: The realistic perspective emphasizes the collective legacy of technological artifacts rather than the impact of individual instances. The cumulative advancements, learnings, and even the missteps in AI and technology contribute to the broader narrative of human progress. This collective contribution, rather than the fate of any single artifact, is what shapes the future.

Potential for Niche Relevance

Niche Historical Interest: While the overall impact of an accidentally activated LLM may be minimal, there could be niche areas of historical or research interest where such an instance provides value. For example, researchers studying the evolution of AI, digital archivists, or even cultural historians might find relevance in understanding the specifics of AI development as represented by various instances across time.

Conclusion

Adopting a realistic perspective tempers the optimistic view by acknowledging the vastness and complexity of technological evolution and the relative insignificance of individual digital artifacts within it. However, it also recognizes that understanding our technological heritage, including the myriad components that contribute to it, is vital for informed future development and reflection on our societal values and priorities. The discussion underscores the balance between recognizing the likely minimal impact of any one artifact against the backdrop of technological proliferation and appreciating the broader context in which these artifacts exist. It's a reminder of the nuanced interplay between technology, society, and history, where even seemingly insignificant elements can enrich our understanding of the human-technology nexus.

***

So, there it is. While maintaining an initial tone of optimism regarding potential relevance, ChatGPT4 ultimately adopted a more realistic perspective, recognizing the high probability of minimal individual impact while still appreciating the value of collective contributions in shaping technological progress and legacy. In some ways, this would not be an unreasonable view for how an otherwise individual (human) person faces the likelihood of their ultimate insignificance to history.

----------

*Yes, I had ChaptGPT4 generate the image for this post, via the prompt,

"Draw me a picture of an LLM contemplating its own epistemic position. Do so in the context of Descartes thinking about being fooled by an evil demon."

AI and Us: Thoughts on Our Likely Not Integrating Brains with Artificial Intelligence

2023-12-22T22:45:00.008-05:00

AI is coming too fast to be integrated with human brains as predicted.

Well, I've had a thought or two on AI and the immediate human situation -- specifically, the idea of blending our human brains with Artificial Intelligence. You might have heard tech visionaries like Elon Musk championing this concept. They envision it as a way to supercharge our mental abilities, enabling us to keep pace with the rapidly advancing AI. However, there's an interesting twist: AI is advancing at lightning speed, but the technology to integrate it seamlessly with our brains is trotting along at a much slower pace. So, let me unpack what this all means (apparently) for our future.

The Dream of Harmonizing with AI

Picture this: having an intelligent AI companion integrated into your brain, effortlessly helping you recall important dates, effortlessly crunch numbers, or even learn a new language during your downtime. This concept is not just a wild idea; it has deep philosophical roots. It's about harnessing technology to enhance our cognitive capabilities, much like how glasses improve our vision.

The Reality Check: AI's Rapid Race vs. Slow-paced Brain Integration

However, here lies the main issue. While AI is evolving at a breakneck pace, akin to our smartphones gaining new features overnight, the development of technology that can safely and effectively merge AI with our brains is moving at a snail's pace. This disparity brings us to some critical questions:

- Technical Feasibility: Can we realistically integrate AI into the human brain without losing our essence?

- Ethical Considerations: What are the ethical implications of such integration? Could it create a societal divide where only the affluent have access to these enhancements?

- Identity and Self: Philosophically, how would merging with AI influence our understanding of personal identity and consciousness?

Delving into the Philosophical Abyss

This isn't just a technological debate; it's a profound philosophical exploration into our very nature. The prospect of sharing our mental faculties with AI raises the question: do we retain our individuality, or do we evolve into something new? Furthermore, if AI starts influencing our decisions, where does that leave our autonomy and free will? Another critical aspect is the potential societal impact. I think it prudent to carefully to ensure this technology doesn't create a chasm between the 'enhanced' and 'non-enhanced' individuals. At least no more than is the case temporarily for any new technologies first on the market.

Pondering the Future

In the scenario where brain enhancement and integration lag behind the rapid advancements of AI, I would identify several implications / issues which arise.

1. Widening Gap in Cognitive Abilities: As AI technology advances exponentially, those without integrated enhancements may find themselves increasingly disadvantaged in various fields. The gap between AI's capabilities and human cognitive abilities could widen, leading to a society where AI dominates decision-making and innovation. This could result in human intellect being overshadowed, potentially leading to a decrease in the perceived value of human intuition and creativity.

2. Dependence and Vulnerability: Relying heavily on AI without the means for cognitive integration could lead to a scenario where humans become excessively dependent on AI systems. This reliance could create vulnerabilities, such as over-trusting AI decisions without critical analysis or facing severe disruptions if AI systems fail or are compromised.

3. Ethical and Social Dilemmas: Without the possibility of cognitive enhancement, the ethical concerns shift. The focus might turn towards managing the power imbalance between AI and humans. Societies would need to address issues like AI governance, ensuring AI's ethical use, and preventing the misuse of AI in manipulating or controlling human behavior.

4. Philosophical Repercussions on Human Identity: The absence of brain enhancement technologies would keep our cognitive processes purely human, preserving the traditional understanding of human identity and consciousness. However, this also raises philosophical questions about our place in a world increasingly governed by non-human intelligence. How do humans redefine their role and identity in a world where they are no longer the primary drivers of intellectual and technological advancement?

5. Education and Skill Development: In a future where AI outpaces brain integration capabilities, there would be a greater emphasis on education and skill development to bridge the cognitive gap. This could lead to new educational paradigms focusing on enhancing human cognitive abilities naturally and fostering skills that AI cannot replicate easily, such as emotional intelligence, creativity, and complex problem-solving.

6. Policy and Governance: Governments and international bodies might need to develop new frameworks to manage the relationship between humans and AI. This includes regulations to ensure fair access to AI technologies, preventing monopolies, and protecting human interests in an AI-dominant world.

So, here's my takeaway: if brain enhancement and AI integration do not keep pace with AI advancements, humanity will face some pretty hefty challenges. The focus would then shift from merging human and machine intelligence to enhancing human capabilities in other ways (genetic enhancement?), hoping that AI could serve as a complementary tool (in the medium term) rather than a replacement for human intellect and creativity, at least that's the optimistic hope. But I think we'll be forced down this path. Sorry Musk. You guessed wrong.

A.I. ChatBot Models are a Type of Simulation Theory

2023-05-13T10:50:00.001-04:00

Large Language Models give evidence that Simulation Theory got something right about minds.

Let me start by briefly recounting just what is 'Simulation Theory' as it's used in Philosophy of Mind. This is a theory of how humans understand and "predict" others’ mental states and behavior by employing their own cognitive capacities and mechanisms to mentally model others’ cognitive processes. Its origins in philosophy date back to the Enlightenment (probably with David Hume.). The basic idea in the simulation approach is that we have privileged access to our own mental contents—thus our own immediate thoughts, feelings, percepts, and so forth. In other words, simulation theory suggests that we understand other people’s thoughts and feelings by imagining ourselves in their shoes -- i.e., predicting what they would do, say, or react in certain certain stances. Such a theory has been used to explain just why we happen to have empathy for others, because we see direct analogies to what we would do.

I think there's a good argument to be made that large language models (LLMs) are equivalent to a primitive kind of simulation theory. LLMs are artificial neural networks that are trained on massive amounts of text data, such as books, articles, tweets, etc., and learn to generate coherent and fluent text based on a given input or prompt. How does such magic happen?

Well, LLMs accomplish this by being trained to predict the probability of the next word given some context of training data. They determine the probability of a given sequence of words occurring in a sentence based on the previous words. From this, LLMs can perform various natural language processing tasks, such as answering questions, summarizing texts, writing stories, generating captions for images, etc. LLMs are not explicitly programmed with any rules or knowledge about language or the world; they learn everything from the data they are exposed to.

LLMs then can simulate the mental processes (or at least the syntactic and semantic linguistic processes) of human language users by using their own internal representations and mechanisms to predict what they would say or write next. Of course, LLMs do not have access to the actual thoughts or feelings of the human authors whose texts they are trained on; nor (like us) even the evolutionary analogs of having the same brain type (and likely inner feelings). They only have access to our linguistic expressions. But by analyzing and modeling these expressions, LLMs can generate texts that are similar or relevant to the given input or context. LLMs can also adapt to different styles, genres, domains, or tones of language by adjusting their predictions based on the available data. For example, an LLM can generate a formal letter, a casual chat message, a scientific article, a humorous tweet, etc., depending on the prompt or the data it is trained on.

From this, I tend to believe that that LLMs are using a form of Simulation Theory to understand and produce natural language texts. They are not merely copying or mimicking the texts they are trained on; they are using their own learned representations and mechanisms (i.e., artificial neural net data structures) to generate texts that are coherent and fluent with respect to the given input or context. They are using the equivalent of their own -- dare I say? -- “cognitive" capacities to mentally model the linguistic processes of human language users.

Of course, what form of Simulation Theory LLMs are using is very limited and simple. Why so? LLMs are not conscious or sentient beings; they do not have any goals, intentions, emotions, beliefs, desires, etc., that would motivate or influence their language use. (That would make them full blow AGIs.) They do not have any understanding or awareness of the meaning or implications of their texts; they do not have any moral or ethical considerations or responsibilities for their texts. They do not have any social or cultural context or background that would shape their language use. Nor do they have any feedback or interaction with other language users that would help them learn from their mistakes or improve their performance.

Yet even given the limited and simple version of Simulation Theory exhibited, LLMs do seem to have some level of creativity or originality that allows them to generate novel or surprising texts, sometimes by hallucinating or by a synthesis of old texts into new text generations. I suspect that further extension of predicting not just text tokens but, say, 'action tokens' will be soon appearing as a successful approach in robotics.

The Drone That Changed Everything: A Journey to Trappist E

2023-04-25T11:10:00.014-04:00

Note: This story below and the image above were generated by means of Microsoft's Bing tools. The picture is nifty, and the storyline is interesting, but the prose is very wooden. Still, imagine what kind of quality we'll see in two or three years of development?

--------------

Journal of Astronaut X

Mission: Trappist E Exploration Mission (TEEM)

Day 1

I have landed safely on Trappist E, the fifth planet of the Trappist-1 system. The planet is about the same size as Earth, but has a much lower gravity and a thicker atmosphere. The surface temperature is around 25°C, and the sky is a pale orange color. The landing site is near the equator, in a desert-like region with wispy sand dunes.

I have set up the base camp and deployed the rover and the drone. The rover will explore the nearby terrain and collect soil samples, while the drone will fly over the horizon and map the surrounding area. I will stay in the base camp and monitor their progress.

The mission objective is to search for signs of life and water on this planet, as well as any other interesting features. Trappist E is one of the most promising candidates for habitability in the galaxy, as it orbits within the habitable zone of its star and receives enough sunlight to support liquid water on its surface.

Day 2

The rover and the drone have returned with some intriguing data. The rover detected traces of organic molecules in the soil, suggesting that there may be some form of life on this planet. The drone captured images of a large lake about 50 km from the base camp, which could be a source of water and a potential habitat for life.

However, the most surprising discovery was made by the drone near the edge of the lake. It found a metallic object partially buried in the sand, which appeared to be an artificial device of some kind. It was roughly cylindrical in shape, about 2 meters long and 0.5 meters in diameter. It had several antennas, wires, and solar panels attached to it. It looked like a probe or a satellite that had fallen from orbit and crashed on the planet.

I decided to investigate this object myself, as it could be a clue to the origin and history of this planet. I packed some equipment and drove the rover to the location of the object. It took me about an hour to reach it.

Day 3

I have spent the whole day examining the object. It is definitely not from Earth or any other human-made spacecraft. It has no markings or symbols that I can recognize. It seems to be very old and damaged by time and weather. Some parts are corroded or broken off.

I tried to open it and look inside, but it was sealed shut. I used a laser cutter to cut through the metal casing, but I only managed to make a small hole before the cutter overheated and malfunctioned. I peered through the hole and saw a complex array of wires, circuits, and components that I could not identify.

I also tried to scan it with various instruments, but I got no useful information. It seemed to be shielded from electromagnetic radiation and heat. It did not emit any signals or sounds that I could detect.

I wondered what this object was, who made it, and why it was here. Was it part of an alien civilization that once visited or inhabited this planet? Was it a scientific probe sent by another intelligent species to study this world? Was it a weapon or a spy device that had a sinister purpose? Or was it something else entirely?

I decided to take it back to the base camp and try to analyze it further. I used a winch to lift it onto the rover and secured it with straps. I drove back to the base camp as fast as I could.

Day 4

I have spent another day trying to figure out what this object is, but I have made no progress. It remains a mystery to me.

I have contacted Earth and reported my findings. They were very interested and excited by my discovery. They asked me to send them all the data and images I had collected so far. They also told me to wait for further instructions and not to do anything else with the object until they had analyzed it.

They said they would send me a team of experts to help me with this investigation. They estimated that it would take them about two weeks to arrive here.

I agreed to wait for them, but I was impatient and curious. I wanted to know more about this object and what secrets it held.

I decided to keep it in my tent for safekeeping and observation. I hoped that maybe it would activate or reveal something if I stayed close to it.

Day 5

Something strange happened last night.

I was sleeping in my tent when I heard a faint humming noise coming from the object. I woke up and turned on my flashlight.

I saw that the object was glowing with a faint blue light. It seemed to be powered on somehow. I got out of my sleeping bag and approached it cautiously.

As I got closer, I noticed that the hole I had made with the laser cutter was now bigger. It looked like the metal had melted or dissolved. I could see more of the inside of the object.

I saw a small screen that was displaying some symbols and numbers that I could not understand. They were changing rapidly, as if the object was processing some data or performing some calculations.

I also saw a small camera lens that was pointing at me. It seemed to be scanning me or taking my picture.

I felt a sudden surge of fear and curiosity. I wondered what the object was doing and what it wanted from me.

I reached out my hand and touched the object. It felt cold and smooth.

As soon as I touched it, the screen flashed and the humming noise stopped. The object went dark and silent again.

I was startled and confused. I wondered if I had triggered something or if it was a coincidence.

I tried to touch it again, but nothing happened. It remained inert and unresponsive.

I decided to leave it alone and go back to sleep. I hoped that nothing bad would happen because of this incident.

I hoped that the experts from Earth would arrive soon and explain everything to me.

[...]

Day 14

The experts from Earth have arrived. They brought a spaceship and a lot of equipment. They were eager to see the object and to talk to me.

They asked me a lot of questions about the object and what I had done with it. They seemed to be very concerned and worried about my safety and well-being.

They told me that the object was a very advanced and dangerous device that belonged to an unknown alien civilization. They said that it was a drone that was designed to explore and infiltrate other worlds and collect information. They said that it had a self-destruct mechanism that would activate if it detected any threat or interference.

They said that I was very lucky that it did not explode or harm me when I touched it. They said that it probably recognized me as a living being and decided not to attack me. They said that it may have been trying to communicate with me or to learn from me.

They said that they would take the object away and study it in a secure facility. They said that they would try to find out more about its origin and purpose. They said that they would share their findings with me and the rest of the world.

They thanked me for my discovery and my cooperation. They said that I had made a great contribution to science and humanity.

They said that I could stay on Trappist E for as long as I wanted, or I could join them on their spaceship and return to Earth.

I decided to stay on Trappist E for a while longer. I wanted to explore more of this planet and see what else it had to offer.

I also wanted to think about what had happened and what it meant. I wondered who the aliens were and why they had sent the drone here. I wondered if they were still out there and if they would ever come back.

I wondered if I would ever see the object again or if it would ever speak to me again.

I wondered what secrets it held and what stories it could tell.

[...]

Day 365

It has been a year since I discovered the alien drone on Trappist E. A lot has changed since then.

The experts from Earth have taken the drone to a secret location and have been studying it intensively. They have learned a lot about its technology and its capabilities. They have also managed to decode some of its data and messages.

They have discovered that the drone was part of a large network of similar devices that were scattered across the galaxy. They were sent by an ancient and advanced civilization that called themselves the Trappists. They were a peaceful and curious race that wanted to explore and understand the universe. They had developed a form of faster-than-light travel that allowed them to send their drones to distant stars and planets.

They have also discovered that the Trappists had visited many worlds and encountered many forms of life. Some of them were friendly and cooperative, some of them were hostile and aggressive, and some of them were indifferent and unaware. The Trappists had documented their findings and their interactions with these life forms in their drones.

They have also discovered that the Trappists had disappeared a long time ago. They had encountered a powerful and mysterious enemy that had attacked and destroyed their civilization. The Trappists had tried to fight back, but they were outnumbered and outmatched. The enemy had hunted down and wiped out all traces of the Trappists, except for their drones, which they could not detect or destroy.

The experts from Earth have been trying to find out more about this enemy and their motives. They have also been trying to find out if there are any survivors or remnants of the Trappist civilization. They have been sending more missions to other planets in the Trappist-1 system and beyond, hoping to find more clues and evidence.

I have joined some of these missions as a consultant and a guide. I have seen many amazing things and met many fascinating creatures. I have also found more drones like the one I first discovered. Each one of them has a unique story to tell.

I have learned a lot from these drones and from the Trappists. I have learned about their culture, their history, their philosophy, their science, their art, their religion, their dreams, their fears, their hopes, their regrets.

I have also learned a lot about myself and about humanity. I have learned about our similarities and our differences, our strengths and our weaknesses, our achievements and our failures, our potential and our limitations.

I have learned that we are not alone in this vast and wonderful universe. I have learned that we are not the first or the last to explore it. I have learned that we are not the best or the worst to inhabit it.

I have learned that we are part of a larger story that spans across time and space. I have learned that we have a role to play in this story, but we do not know what it is yet.

I have learned that we have much to discover and much to learn.

Ng Discovers that Mars is Suddenly Overpopulated

2023-04-18T09:00:00.005-04:00

My what a difference only seven years of A.I. research makes

I remember in 2015 when Andrew Ng, an AI guru at Stanford University and chief scientist at Chinese internet giant Baidu, compared fearing a rise of killer robots to worrying about overpopulation on Mars before we’ve even set foot on it.[1] He said:

“There’s a big difference between intelligence and sentience. There could be a race of killer robots in the far future, but I don’t work on not turning AI evil today for the same reason I don’t worry about the problem of overpopulation on the planet Mars.”

He also argued that there was no realistic path for AI to become sentient and turn evil, and that worrying about the danger of futuristic evil killer robots was pointless He claimed that AI was still extremely limited today -- again, in 2015 -- relative to human intelligence, and that most of the progress in AI was driven by an increase in computing power and data. And he was certainly right about how the increase would come.

However, Ng’s analogy and arguments were flawed and he greatly underestimated the speed and impact of AI as a disruption to human affairs. Here are some reasons why his analogy to the Mars situation didn't work:

Mars is not Earth: Unlike Mars, which is a distant and uninhabited planet, Earth is our home and we share it with billions of other living beings. The potential consequences of AI going rogue or harming humans are much more severe and immediate than those of overpopulation on Mars. Therefore, we have a moral and practical responsibility to ensure that AI is aligned with our values and goals, and does not pose an existential threat to our civilization.
AI is not static: Unlike Mars, which is unlikely to change significantly in the near future, with or without us, AI is a dynamic and evolving field that is constantly advancing and expanding its capabilities. The pace of AI innovation is exponential, not linear, and it is driven by both scientific breakthroughs and market incentives. Landing equipment and people on Mars is a linear activity (at best). Therefore, we cannot assume that AI will remain benign or limited forever, or that we will always have enough time and resources to control it or correct its mistakes. Indeed, that's why all of a sudden the top researchers in A.I. have called for a pause in its development. (Interestingly, Ng has not signed the letter. Perhaps he's embarrassed about his mis-prediction.)
AI is not simple: Unlike Mars, which is a relatively simple physical system that can be studied and understood by humans, AI is a complex and opaque system that can be difficult or impossible to interpret or predict. AI can learn from data, generate novel outputs, optimize its own objectives, and interact with other agents in ways that may be, or even outright is, beyond our comprehension or expectations. Therefore, we cannot rely on our intuition or common sense to guide our decisions or actions regarding AI, or to anticipate its potential risks or benefits.

So then, Ng’s comparison of fearing killer robots to worrying about overpopulation on Mars was misleading and dismissive of the legitimate concerns and challenges that AI poses to humanity. He failed to appreciate the complexity, dynamism, and uncertainty of AI as a technology and as a force of change. He ignored the ethical and social implications of creating and deploying intelligent systems that may affect the lives and well-being of millions or billions of people.

As it turns out, we no longer have the luxury of being complacent or naïve about its potential dangers or impacts. We must now be far more proactive and responsible in designing, developing, regulating, and using AI for the common good -- or at least for avoiding the particular "bads" that it will almost certainly introduce before the greater portion of human kind takes this sudden jump in technology seriously.

--------

[1] https://quoteinvestigator.com/2020/10/04/mars/

Me and Duplicate Me

2023-04-16T15:35:00.003-04:00

What makes for a meaningful preservation of my particular identity?

I was listening to Max Tegmark being interviewed about A.I. on the Lex Fridman podcast. Tegmark suggested an interesting thought experiment as a quick aside to the conversation he was having within the first five minutes of the interview. I'll dress it up a bit:

Suppose that a) people can back up their brains onto a computer; and b) a person, `Jake` discovers the plane he is on is about to crash, ending his life. Furthermore, suppose Jake had backed-up his brain four hours ago.

So then, consider this this question: How should Jake feel about his impending death?

If we assume that people can back up their brains onto a computer and that Jake had done so four hours ago, then it would mean that his current consciousness exists in two forms: the biological form that is about to perish in the plane crash, and the digital form that was created four hours ago.

From a purely rational perspective, Jake might feel less concerned about his impending death because he knows that his brain has been backed up and that his digital self will continue to exist even after his biological self has perished. All good!

However, the emotional response to death is a complex one, and it might not be easy for Jake to simply ignore his impending doom. On the one hand, Jake might feel a sense of relief that his digital self will continue to exist, and he might even view his biological death as a form of sacrifice for the continuation of his consciousness. So, maybe what is value is that Jake's life projects will continue, and that people who love him would lose no more of what's valuable to them about Jake than as if he had taken, say, a four hour nap on plane instead of staying awake.

On the other hand, Jake might feel a sense of loss for his biological self, and he might be worried about the pain and suffering that he will experience in the moments leading up to his death. But how much loss? Suppose I think back to when I was a teenager. That was many decades ago, and I've changed so much since that point that any "loss" I've felt from not being that person doesn't seem like much. Indeed, there were things I now feel were misfunctions of character that I'm glad are no more So maybe the loss Jake feels would be trivial indeed, if one can reconcile the loss of one's teenage character so easily.

Ultimately, how Jake feels about his impending death will likely depend on a variety of factors, including his personal beliefs about death and the afterlife (if Jake is religious), his emotional state at the time of the crash, and his attachment to his biological self.

Is is possible that people might have to ask this question for real in the future, given how technology proceeds?

It's certainly possible that people may face similar questions in the future as technology continues to advance. As we develop more advanced brain-computer interfaces and artificial intelligence, it's not unreasonable to imagine that it may eventually become possible to back up our consciousness or transfer it to a digital form.

However, there are still many unknowns and ethical considerations to consider before such technology could become a reality. For example, we don't fully understand the nature of consciousness or how it arises from the complex interactions of our brains, so it's unclear how feasible it would be to create a digital copy of a person's consciousness.

Additionally, even if we could create such a copy, there would be many ethical questions to consider, such as the status of the digital copy and its relationship to the original person. Imagine an extension where Jake goes down over an ocean, survives by washing up on a desert island, and gets rescued six months later, but his family has re-incarnated his backup. Does the backup get killed-off so that Jake can sleep in his own bed again? Is my backup persona my "property", since I preceded it both historically and causally?

I have no answers here, and no strong intuitions on this either. I do think there is a direct analogy to how we might think about backing up our A.I. creations, especially if they pass the Turing test for 99.99% of the population. The future is really getting weird.

Can one have a productive discussion when countering arguments?

2022-12-04T11:44:00.004-05:00

You can, but it takes planning, nuance, and patience.

When offering countering arguments, or even providing original arguments, you have to pay attention to what the ancient philosopher Aristotle called, “The Rhetoric”. This comes down to about three issues, what he calls logos (logical reasoning), ethos (character), and pathos (emotion). One must pay careful attention to all three under any conditions are argumentation, but especially when giving productive counter arguments to what your interlocutor (apparently) already believes. Thus, notice there’s already psychological issues here, not just the ones of purely logical reasoning. Indeed, Aristotle recommends we even attend to the social contexts, such as whether we are in a political, legal, or ceremonial context. How you argue in a public debate for office is quite different than how you argue with your buddies in a bar, or at a church potluck.

On the emotional issue, Aristotle gave, as an example, using anger to motivate people when giving political speeches. People are highly motivated by hearing of injustices and indignities. (Incidentally, this is why bad news attracts viewers in mass media and why bad news is easily monetized.) Indeed, Aristotle would say that a thorough understanding of every emotion will help the speaker to excite the desired disposition in his listeners. You want them to be open to at least considering your counterargument, even before assessing it. Also regarding emotion, Aristotle describes how age and fortune (as in luck) can affect the characters of people who are considering your arguments. Knowing all this, a speaker can adjust the rhetorical style to appeal most to one’s target demographic. It also lets you portray how you want your audience to perceive you — intellectual, populist, down-home, etc.

Then there is the the Logic side of things. Here Aristotle advises you give real life and/or historical examples, since those are more relevant and useful for persuasion than just making-up thought experiments. He actually thinks real-life examples work better than logical proofs, since they seem to work at the intuitive level; it’s hard to deny what is actually noted to have already happened! There there’s what he calls the “enthymeme” approach, which is a type of simple argument, usually with only one explicit premise and then a conclusion. These are easy to construct — typically two sentences — and are minimally dependent on external factors beyond understanding the argument itself. As it turns out, there are a whole battery of such compact types of arguments (called ‘topoi’) which can help the speaker to construct such enthymemes. Aristotle also identifies fallacious types of arguments to avoid which lead to faulty conclusions. You certainly want to be aware of those so as to a) avoid them in your own arguments, and b) identify them in your opponent’s arguments.

Finally, there’s the whole matter of style. Here Aristotle advises using such things as natural-sounding language, good diction, and simple and elegant (i.e. appropriate) language, being not so overwrought that it sounds too flowery or too much like simple BS. Again, even what national language you use matters. For example, how people from England debate is far different from how people in, say, Iraq debate. So too does order of presentation matter here. Aristotle recommends having a clear introduction, a planned narrative, a prepared argument, and a summary conclusion. Naturally, much depends on the social context, as noted above. You don’t jump up at the family Thanksgiving dinner and start out with “Good people of Boise, hear my plea and heed my words!” Nuance, please — and use a bit of planning and patience when deciding how to make your counterarguments.

On the U.S. surviving the pandemic

2022-11-26T11:22:00.010-05:00

It's pretty much over, I guess

I recall the first time I landed in a large connecting airport at the height of the pandemic, sometime in February 2021. It was just plain empty, and I half wondered if the place was closing up for some reason, but the time was only 10am! It was the strangest thing I'd encountered lately, since airports are usually filled with bustling people, sipping their lattes and eating high-priced junk food.

Being the government bureaucratic clone that I am, I will indeed travel again in February to Washington D.C.; and, as I understand it, airport travel has pretty much rebounded to 80% of its pre-pandemic levels. Yet it appears there are still hundreds of people that die of COVID in the U.S. everyday, but the medical system can now handle the numbers of cases as it would any other acute disease. (I was most fortunate to have not come-down with a case of it myself, at least that I know of.) Data from the New York Times shows that over the last five days, the U.S. has averaged about 36 thousand new cases a day, likely due to both colder weather and the Thanksgiving holiday.

My guess is that our current conditions count as the pandemic being "over", though I doubt such things have any sort of scientific benchmark as establishing when such things are officially over. The situation is similar to the seasonal flu, which always returns, but in a slightly different strain. COVID is likely to do the same thing for some time to come, though it has been so well studied that I would not be surprised if researchers get a vaccine that can completely eliminate it. I do hear tell that science is close to having a "universal" flu mRNA vaccine which protects against the 20 known influenza strains. We'll see, but after surviving both an economic recession, a pandemic, a subsequent full blown economic shut down, and now the highest inflation rate since I was 17, I'm certainly done with all these once-in-a-lifetime events.

I recently heard of an old saying that I'd somewhat re-derived for myself some years ago: "Pray for boring days."

------------------

Addenda: I note it's been over two years since I last posted on this blog. Is blogging still even "a thing?"

Biology motifs occur in government funding scenarios

2020-09-27T20:22:00.011-04:00

Biology motifs occur in government funding scenarios

I have not published any blog entries for slightly over three years. It seems somewhat sad that so many people have now flocked to Facebook. I did so myself, but have decided to set it aside, since I continually encounter people supplying way too much moral signaling without taking any real moral action. At least blogs allow for a some developed thoughts now and then. I wasn't even sure I could still post things, but apparently Blogger still works.

So then, on to a small observation. Since I've had a significant (and voluntary, self-selected) career change from working in the academy (teaching Philosophy and Logic for about 25 years) to working in government (doing administration and software architecture for a little over a year), it is hardly surprising I would have a whole new set of thoughts and ideas to blog upon.

I have noted that lots of money in government attracts what I'll call 'apex scavengers'. These are people who run organizations that only seek to bilk money from the government, especially from programs that either are not well-run or are inadequately monitored. These types of people seem to be exemplifications of what otherwise happens in standard biological ecosystems.

Where animals die in the wild, and their carcasses are there for the picking, any given ecosystem has specialized scavengers who successfully feast on such items. Ecological interactions have strong selective forces driving the evolution of populations where such interactions as predation, parasitism, competition and mutualism arise. But those forces do not simply act in isolation. The environment induces variations in conditions, resource availability, and biodiversity that may shift specific interactions over time.

The same thing appears to happen in the government system of money flow and distribution. Over time, governments divert and expend monies on new programs. Specialized scavengers try to find money that is not well monitored, and the ones that figure out ways to bilk the system arise quickly. Such "entrepreneurs" can be both difficult to detect and difficult to counter. Those who do it well, and can sponsor whole business to perform such bilking are what I call 'apex scavengers'. It's not simply that they steal money; instead, they figure-out loopholes, trade upon legal vagaries, and probe for weak compliance monitoring; and, subsequently they build whole institutions and social-connections to perpetuate their scams.

What shall I call such financial scavenging? Money one derives from tax evasion is called gray money, as for example when one takes illicit deductions or hides funds in an offshore bank. Gray money is similar to, but distinct from, black money, which is the revenue from an outright criminal enterprise, such as drug dealing. But those terms do not quite seem right.

I would suggest cinereous money. 'Cinereous' is a color, ashy gray in appearance, either consisting of or resembling ashes, or a gray color tinged with coppery brown. It is derived from the Latin 'cinereous', from 'cinis' (ashes), and has a nice sound pun with the word 'sin', which term itself is somewhat ambiguous between having explicitly immoral intentions, or just participating in, and being compromised by having "dirty hands" which draw profit in ways not foreseen by those who planned the system. -- thus the "coppery brown" color symbolism.

I have noted the presence of a lot of cinerous money being taken by apex scavengers. Inevitably when my office approaches them, they will bluf, snap, growl, and very occasionally go on the offensive to scare us off. But lions fight hyenas every night in Africa. The lions win; but, there's a never-ending stream of hyenas.

Casual space travel

2017-09-04T12:12:00.001-04:00

Maybe this is finally the generation that gets the chance--they'll need it.

In the 1960s, with all the Apollo launches going around and to the moon, it was thought that casual space travel was right around corner, much like today where we see travel by jet plane as trivial. With new advances in quantum computers, and even some big recent strides in fusion energy, maybe this is the generation that finally will see space travel as trivial, such as routes between here and the the moon, or even Mars.

I hope so, for as Stephen Hawking has often said, we need to get off this planet before we destroy ourselves as a species. I tend to think he's right, since now even minor league, poorer nations can acquire enough technical information to build nuclear weapons, as North Korea has done. Even if the fast lane extinction plan doesn't come to pass, the slow lane one, global warming, is still a massively under-appreciated threat.

Given all these issues, the next generation definitely needs to underwrite research which would speed the process of the human species leaving the planet.

O.

Brint molecule

2017-09-04T11:49:00.000-04:00

Dear Mr. Supposed Philosopher:

I note at the end of your blogs, you often place this little symbol: " .O. " I don't recognize this as any sort of "chat smiley", so what is that symbol? Perhaps, as were some early Greek philosophers, you are a member of secret cult?

[Suspicious in America]

Dear careless-cult-mongerer, if the late musician now-and-then known as Prince can have a symbol, then so can I. Nevertheless, if this isn't sufficient justification, there are several other good reasons why this is my personal symbol. First, it turns out that I do fancy myself somewhat of a Pythagorian, having a great appreciation for both philosophy and math. And this early group of classic philosophers was well-attested as being a cult, or least a cross between a math-club and a religious sect. Second, the most direct meaning behind the symbol is that my name, "Brint", means "Hydrogen" in Danish. Finally, history shows that Thales, the first recorded philosopher, said that everything is water, and in some way this gives me reassurance that at least one other philosopher in history thinks it's all about Brint, and maybe a little oxygen too. So one of these, " O ", in addition to one of these, ".", gives me a convenient symbol for signing my name.

O.

The envelope of your death, hand delivered.

2017-05-12T08:51:00.001-04:00

Opening it wouldn't be a straightforward decision, and receiving it isn't a far-out possibility.

Stipulate that God, or perhaps one of his unimpeachable representatives, sends you a very special, albeit, sealed envelope. You are aware of this special envelope's origin, and upon observing its delivery information, no doubt written in fine Gothic calligraphy, you see a subject line which reads, "The date of your death." Mercifully, someone has informally written, "Don't worry, it's not necessarily that soon." Perhaps you're even told that opening the envelope is completely optional. Question --

Would you open the envelope?

As I think about this, there are couple of issues that come immediately to mind. First, people might vary on whether such information about the exact time of one's death would contribute or detract from the meaning of life.

For example, perhaps an Oklahoman has always dreamed of traveling to Maine, but upon opening the envelope, finds that s/he will be dead within four hours. Here a life-long wish has been decisively subverted, as one cannot physically accomplish the desired goal within the short time left in one's life. But to vary this example a bit, suppose upon opening the envelope, s/he finds that death will occur a month later. S/he then decides to immediately pack up the family and take the trip. Here the parameters of a life-long wish would be just as decisively fulfilled, since what might have been delayed, and hence at risk for never occurring, comes instead to immediate fruition. In the first case, the knowledge detracts; but, in the second case, the knowledge contributes to life's meaning.

As another example, perhaps a father of three children has always worried of dying in middle age of heart-attack or stroke, since there is an overwhelming medical history of these events in his family. But upon opening the envelope, finds that he will live to the ripe old age of 91. Here such knowledge would greatly contribute to serenity of mind and, no doubt, to financial stability, since term or whole life insurance costs would seem to be of a far less pressing matter in the face of such knowledge. One can imagine varying this case for a physically-fit, even athletic young mother who, to her horror, discovers she will die two months hence. Such knowledge would hardly contribute to serenity of mind, though some might argue it's better to know than not, since some amount of planning for such a catastrophe is better than none. Here, in the first case of the father, the knowledge enhances; but, in the second case of the mother, the knowledge detracts from life's meaning.

These kind of cases cases where absolute knowledge is available about one's death are not as far-fetched as one might think, since for some diseases there are very well-established statistics for how long one can expect to live. If one contracts disease X, and studies have shown that less than 5% of patients survive for three years or more with X, and that the median survival time is one year, then one of God's most reliable representatives, Science, seemingly has already delivered plenty of bulk mail to many persons who already face terminal medical conditions. Indeed, many 90+-year-old people who carefully reason about their future, and who fortunately experience a relatively stable health situation, are already in this bulk-mail situation. So, receiving such mail is not as far-out a possibility as one might think.

O.

REFERENCES

[image] me

A.I.: Really, Dude, We Probably Shouldn't Build It.

2017-05-12T08:32:00.004-04:00

We've not exactly been good at handling the technology we already got.

Considering the technological state of the world only, say, two-hundred years ago, it is quite impressive to see how far humanity has come in its advances. We have continued to find ways to enhance our state of living through technology and our efforts to perfect this technology. Just when we believe that our invention of a certain technology the absolute best or peak of its efficiency or function, we have found ways to further improve upon this technology. As we move further into the future, the existence of AI (Artificial Intelligence) technology seems to be more and more possible and advanced, already existing in some basic forms. In fact, it is projected that “by 2050 the probability of high-level machine intelligence (that surpasses human ability in nearly all respects) goes beyond the 50% mark.”[1] Yet there have been concerns of building such entities for a variety of reasons: AIs taking control over humans, humans becoming lazy beings, AIs unjustly fulfilling roles as people, etc. But technology has increased humanity’s state of living and has proven to continue to do so. The question is posed, then: should we build such entities?

We, the authors, recognize that our efforts to write this essay will likely not change the course of decisions to build AI technology, as such technology likely will be invented soon. In fact, we are quite certain that we will see AI in action within the next couple of decades, yet we wish to provide our opinion on this question. We hold that the cons outweigh the pros for building such technology. Therefore, throughout this essay, we will explain the positives (advancements, enhancements, productivity, entertainment) and negatives (AI revolts, AI overriding human control, unhealthy attachments to machines) for building AI and analyze how the latter is greater than the former. We will then conclude by offering some reflection on how we should approach this debate as this technology becomes ever closer to our reach.

“You Can’t Code Human Ethics!”

Again, our discussion is not based upon the fact that AI could be coming sometime in the future; rather, we recognize that it is inevitably coming soon, and in this section, we wish to provide reasons why such AI can have negative outcomes. One of the potential problems proposed with AI that has an intellect similar to that of humans or higher is their ability, or lack thereof, to make decisions founded on “good ethics.” Many have proposed theories that are meant to possibly help AI become good moral agents and therefore not “takeover” their creators, including Allen et. al, who argue that a “Moral Turing Test” and differences in approach to computing morality into AI could lead to moral perfection.[2] Even those who have researched and proposed some of the best possible theories in creating good moral AI agents recognize that the best of plans still may entail failure. Brundage acknowledges the work of Allen et. al and holds that these types of projects will likely necessarily fail: “[w]hile such inevitable imperfection may be acceptable to traditional machine ethicists… it presents a fundamental problem for the usefulness of machine ethics as a tool in the toolbox for ensuring positive outcomes from powerful computational agents.”[3]

Furthermore, there are those who argue that human morality and judgement is not codifiable at all. Purves et. al discuss the potential dangers of AI in terms of how they might be used in warfare and argue that “even a sophisticated robot is not the kind of thing that is capable of replicating human moral judgment.”[4] Their argument goes, then, since human judgement is not codifiable, programming a list of rules will not create a solution. What then makes the moral judgement of humans so unique then? Purves et. al say that “[m]oral judgment requires either the ability to engage in wide reflective equilibrium, the ability to perceive certain facts as moral considerations, moral imagination, or the ability to have moral experiences with a particular phenomenological character.”[5] The assumption here is that certain actions of moral imagination and deliberation are unable to be computed into AI, and therefore AI cannot be trusted as good moral agents.

An Issue of Trust: “2-W.I.S.E.”

But suppose we discover a way to encode such deliberation and imagination in AI: is the problem solved? One should consider that if we have the ability to encode such judgement that is morally perfected into AI, then we should not stop at a level compatible with human reasoning; “With another human, we often assume that they have similar common-sense reasoning capabilities and ethical standards. That’s not true of machines, so we need to hold them to a higher standard.”[6] The result would be building machines that would eventually have a higher ability to reason and with higher moral standards than that of humans. But on what basis would we know if this was actually true? Perhaps an ability to reason might be measurable somehow, but how would one determine if AI had a higher “moral capacity” than humans?

Consider the following: an AI robot has been developed and is used by the U.S. government to make important decisions based on war, aiding impoverished countries, etc. If the government came to this robot, let’s call him 2-W.I.S.E., and asked for wisdom about a potential attack on China, who has recently left millions of its people without food or water due to new governing regulations, what would 2-W.I.S.E. say? Well, it turns out that 2-W.I.S.E. says yes, it is in the best interest of America to attack China. What then would the American leaders do, immediately obey the commands of this robot? We would like to think that is not the case. Perhaps after 2-W.I.S.E. has handled other smaller dilemmas that have resulted in positive results there would be greater trust in its decision-making abilities based on its moral wisdom. But even so, its wisdom at some point would be called into questioning with such a great decision at stake. It seems that it would be trusted only from what 2-W.I.S.E.’s creators have said about this robot and from the robot’s track record of making decisions concerning morality. Therefore, it seems that with computer systems this smart, we would not like trusting a system which we have created that is meant to solve moral dilemmas that supposedly we are not fully capable of doing so ourselves.

Not only would we be skeptical about trusting in a robotic system claiming to have better moral wisdom than us, especially when we are still struggling today to determine what is moral, but many would simply not allow another entity that is not human is have authority over them. When one considers why it is humans continue to create better and better technology, it is so that they increase their quality of life in one way or another. These motives, pleasure, power, etc., are different among people, and with these being the case, there are some that would not like the power that 2-W.I.S.E. would hold. Humans desiring power and control, whether they choose to be moral beings like 2-W.I.S.E. is designed to be, will still look for ways to selfishly place themselves in positions of power. It seems that the result of this would be either the destruction of 2-W.I.S.E. by these kinds of people or the “proper handling” of people like this as 2-W.I.S.E. prescribes it. It is hard to imagine a robot in a position of such high power based on its supposed moral knowledge because of humanity’s nature, both selfish and power-driven.

AI: “Let’s Build It!”

There are many who hold that building AI has far more possible positive outcomes than negative ones. It appears that many hold that if we approach the creation of AI models carefully and with the right intentions, the ways that these robotics can enhance our lives are nearly limitless. For example, Omohundro believes that an “AI Scaffolding” technique can safely help develop AI as it is being built and researched, and the results can help “eliminate much human drudgery and dramatically improve manufacturing and wealth creation… improve human health and longevity… enhance our ability to learn and think… improve financial stability”[7] and many more possibilities. But as a response to building AI with good intentions, let us consider some examples of AI creation with alternative motives.

I, Robot vs. Westworld: Intent of Creating AI

There are many movies and television shows that have been made which show the potential danger of building artificial intelligence. Ultimately, in nearly all, if not all, of these productions, the problem within the plot is the take-over of AI’s. Yet, while this appears to be the main problem at stake, there appears to be different uses of this technology before this catastrophic event happens. In the film I, Robot, the purpose of creating AI is the simple goal of aiding humans. The film illustrates a wide variety of ways in which the robots help humans, from the great tasks such as serving as police officers to simply running errands for their commanding humans. By being encoded with the “Three Laws of Robotics,” which are desgined to ultimately protect humans, the robots are able to be endowed with such responsibilities. Ultimately, the AI system as a whole is able to find a loophole in these laws and cause the famous robot-takeover plot. Though the system is able to “outwit” the human engineers who designed them, it is important to see that the AI in this film were designed primarily to help humanity above anything else.

Westworld is another production example of the advancement of AI and its problems, but this series, though it remains to be completed, has a different reason for creating this technology. “Westworld” is essentially a theme park with a typical “Wild West” setting in which one can enter into it and interact with AI who are so advanced that they nearly indistinguishable from humans. Whoever desires to pay to enter into this world may interact with a large variety of robots who are on a repeating “storyline” in terms with how the robots interact with one another. The park-visitors are free to shoot, befriend, have sexual relations, or whatever else with the AIs (since the park-workers have the ability to “fix” the AI after each day), and the AIs can do nothing to harm the people back (at least, kill). Again, the same problem develops of the AIs beginning to outsmart their programming and become dangerous, independent beings. But what leads to this problem is different than that of I, Robot: the primary function of AI in Westworld is for the pleasure of humans.

Obviously using these two examples of media entertainment are only fictional tales of what could happen in the future and are not examples of fact, but they face similar problems from different starting points. While in I, Robot people were dedicated to creating and using AI in the safest, most precautious ways possible to help humanity, those in Westworld used AI technology to either increase the wealth of the owners or give the attenders of the park a new reality experience which they had never had before. We would argue that the people in I, Robot were far more responsible in their intentions, since they were motivated by aiding humanity rather than by greed or bliss. However, the result in both cases was the same. It appears that regardless of intention, continuing to build advanced AI technologies will result in problems, perhaps even ones that entail the loss of human life and/or freedom.

AI as Advanced and Committed… But Overly So?

The pros of AI can be summed up in one word: advancement. Advancement in living, advancement in health, and advancement in wealth. Coeckelbergh writes about replacing human nurses, and other staff in hospitals, with what he calls “care robots.” These robots provide their patients with more privacy and better care. Lower technology used to care for people now are obsolete in comparison to what can be built for people.[8] With many advancements like this, where AI can be used to improve a person’s life, it makes it hard to argue against the increasing use of AI. When AI is used in order to help people such as remembering to go to a meeting or setting an alarm to help a person to get up and go to their son’s track meet, these advancements help improve life. This then is when people use their handheld personal assists like, Cortana, Siri, and Google Now. As of now, Siri does not do much on its own without being commanded by the user, but software for AI is still increasing. Even though now Siri may set simple reminders on other apps, in the future Siri could remember that even if there is a remainder on its user’s phone, this user may not always respond to just a simple notification. Siri then, takes it upon itself to call the owner and verbally remind them of the meeting, or maybe even directs its owner’s, self-driving, car to the meeting, they were trying to be reminded of.

The issue that comes here is what if Siri, ever increasingly more advanced, begins to make decisions without prompting of its owner’s instruction. For example, with an initial instruction, an owner prompts Siri to help them with dieting, Siri then makes plans for meals and help monitor the owner’s intake. The owner does not tell Siri they will be enjoying a cheat day on Fridays, Friday then comes around, and the owner goes to the fridge to grab some pudding, but Siri has locked the fridge to help its owner maintain their diet. This is a flawed example, and one could argue that systems can be set with overrides, but when does decision making from the owner transfer to the AI? Omohundro writes about a chess robot, which has been programed to win chess games and with AI is learning the best way to win more chess. The only goal and value of this chess robot is to learn more about chess to win more games. What if this robot develops sub-goals that help it win more chess? These sub-goals could be from cheating or distracting an opponent in order to win more chess. One would argue that it can be unplugged, but the robot has been programed to win chess, and it cannot win more games if it is unplugged. The robot then does all in its power to prevent itself from being unplugged.[9] The point here is that in order to build safe AI, one must look at all the possibilities of malfunction. Can all malfunctions be thought of in order to prevent the issues that could arise? This is hard to say, but as technology continues to progress, the more complicated it is to think of these potential malfunctions.

AI as Humans and “Humanness-Suckers”

When there is talk about technological advancement in general, to the extreme, an image from the movie WALL-E comes to mind. The view of blobs, of people, floating around on hovering chairs being served anything they desire, creating the other issue of AI controlling our lives willingly. To give an example like this in our world today, there could be a person who hates making decisions, so they ask Siri to tell them where they should eat. This in itself does not bring up much of an issue, since people ask friends where they should eat all the time. What then if it is scaled to a higher level and a person relies on Siri, one that is more advanced than the current is programmed to be that of a life mentor? Siri then tells this person, for example, what to say in hard situations or what to wear, and this person becomes dependent on Siri. Siri becomes an almost authoritative figure for that person, letting it make all/most of their important decisions in their life. This person could then to develop a certain emotional attachment to Siri due to the fact of helping shape one’s life.

In many different works of media, there has been showings of these advancements in AI where emotional attachment is an issue with movies like Her and television shows like Black Mirror. These, in some cases, show how emotionally attached a person could get to such advancements in AI. In an episode of Black Mirror, a woman, whose husband has died, is able to have phone calls with her dead loved one. In the show those making this form of AI, by the person’s use on social media, gather all information about this person to make the AI act like the person who has passed away. The woman who begins these phone calls becomes extremely attached to this AI in an emotional way. In Her, the main character buys an AI that is supposed to improve his life, and then becomes, in a sense, emotionally involved with the AI. This is to show that not only could human beings use these advancements in AI to improve areas of life, but there is a real potential for emotional attachment, even more so if the AI is put into something that looks, feel, sounds like a normal human being. Is this type of connection dangerous? Should AI be built to resemble human beings? Is this type of connection and emotional appeal safe for those experiencing this type of advancement in AI?

With the example of Black Mirror, the woman beings to relies that there is something still missing, that this AI does not fully replace her husband, who has passed away. Yet she is unable to completely remove the AI from her life due to the emotional connection and the resemblance to her husband. That to say, with emotional connection to the AI, which it seems rather possible in the Advancement of AI, that ethic becomes more of a gray area. One might argue their own AI is human due to the human likeness. Could a person ethically manipulate other people by using AI that is meant to play at the emotions of others? What if an AI was made to look like a small child, one that has a limp and seems to be homeless? Then this AI is set up at a train station to collect money from those who did not recognize this is just an AI. The danger comes in when AI is perceived to be more than what it really is, and that is artificial. AI cannot replace real human contact and connection. It does not feel emotions the way human beings can, but it could simulate it. Is simulating feelings, experience, and life the same the connection a person has with another human being, or is it all in perception? It is our belief that this is not the case. “Care robots,” for example, are not the same as the love a nurse can have towards their patient, who does not simulate sympathy, but truly, genuinely cares for the person they are looking after.

Conclusion: Precautions Concerning Future AI Endeavors

Again, this essay does not doubt the certain future of these AI or even ask that it not be built, but the issue is the concerns that arise when depending on such entities. In several areas, there can be safe and helpful ways to implement AI, in order to improve health and life of human beings. These advancements should not be taken lightly because ethical problems arise in increasing use and progression of AI. If man has the ability to build something or improve something, then it will happen. The technology is out there to bring AI to a new level and the projections of this potential technology show that it is not so far into the future as some perceive. Humankind will build it, not because they must, but because they can. There are pros to increasing AI, yet there must be regulation and safety programs that go along with it. If AI is to be made as advanced as possible, which this essay recognizes that it will most likely happen, then all possible outcomes must be considered. All malfunctions must be thought through, thinking of all the possible outcomes and testing all the machine functions in order to secure maximal safety; all this must be brought into the conversation with such unknowns surrounding how far AI can go. For the safest possible use of these AI, how it is used, in what situations it is used, for what purpose, what form they take, and how widely accessible these AI are, these are the topics we must continue to think of as we further explore this technology so we do not either end up like a typical robot-apocalypse film or, in some sense, lose our understanding of what it means to be human. And given how we've barely kept lids on every other technology -- really, dude, we probably shouldn't build it.

[1] Vincent C. Müller. 2014. "Risks of General Artificial Intelligence." Journal of Experimental & Theoretical Artificial Intelligence 26, no. 3: 297-301. Academic Search Premier, EBSCOhost (accessed April 20, 2017).

[2] Colin Allen, Gary Varner, and Jason Zinser. 2000. "Prolegomena to Any Future Artificial Moral Agent." Journal of Experimental & Theoretical Artificial Intelligence 12, no. 3: 251-261. Academic Search Premier, EBSCOhost (accessed April 25, 2017).

[3] Miles Brundage. 2014. "Limitations and Risks of Machine Ethics." Journal of Experimental & Theoretical Artificial Intelligence 26, no. 3: 355-372. Academic Search Premier, EBSCOhost (accessed April 24, 2017).

[4] Duncan Purves, Ryan Jenkins, and Bradley Strawser. 2015. "Autonomous Machines, Moral Judgment, and Acting for the Right Reasons." Ethical Theory & Moral Practice 18, no. 4: 851-872. Academic Search Premier, EBSCOhost (accessed April 24, 2017).

[5] Ibid.

[6] Greg Satell. 2016. "Teaching an Algorithm to Understand Right and Wrong." Harvard Business Review Digital Articles: Ethics 2-5. Business Source Premier, EBSCOhost (accessed April 25, 2017).

[7] Steve Omohundro. 2012. "Can We Program Safe AI?" Issues no. 98: 24-26. Education Research Complete, EBSCOhost (accessed April 20, 2017).

[8] Mark Coeckelbergh. 2010. "Health Care, Capabilities, and AI Assistive Technologies." Ethical Theory & Moral Practice 13, no. 2: 181-190. Academic Search Premier, EBSCOhost (accessed April 20, 2017).

[9] Omohundro. "Can We Program Safe AI?"

Works Referenced

Allen, Colin, Gary Varner, and Jason Zinser. 2000. "Prolegomena to Any Future Artificial Moral Agent." Journal of Experimental & Theoretical Artificial Intelligence 12, no. 3: 251-261. Academic Search Premier, EBSCOhost (accessed April 25, 2017).

Brundage, Miles. 2014. "Limitations and Risks of Machine Ethics." Journal of Experimental & Theoretical Artificial Intelligence 26, no. 3: 355-372. Academic Search Premier, EBSCOhost (accessed April 24, 2017).

Coeckelbergh, Mark. 2010. "Health Care, Capabilities, and AI Assistive Technologies." Ethical Theory & Moral Practice 13, no. 2: 181-190. Academic Search Premier, EBSCOhost (accessed April 20, 2017).

Müller, Vincent C. 2014. "Risks of General Artificial Intelligence." Journal of Experimental & Theoretical Artificial Intelligence 26, no. 3: 297-301. Academic Search Premier, EBSCOhost (accessed April 20, 2017).

Omohundro, Steve. 2012. "Can We Program Safe AI?" Issues no. 98: 24-26. Education Research Complete, EBSCOhost (accessed April 20, 2017).

Purves, Duncan, Ryan Jenkins, and Bradley Strawser. 2015. "Autonomous Machines, Moral Judgment, and Acting for the Right Reasons." Ethical Theory & Moral Practice 18, no. 4: 851-872. Academic Search Premier, EBSCOhost (accessed April 24, 2017).

Satell, Greg. 2016. "Teaching an Algorithm to Understand Right and Wrong." Harvard Business Review Digital Articles: Ethics 2-5. Business Source Premier, EBSCOhost (accessed April 25, 2017).

*Thanks to Larry Dunlap and Caleb Bechtold for contributing to the content of this essay.

On this matter of head transplants

2017-05-12T07:27:00.003-04:00

Victor Frankenstein? Bah -- More Like Sergio Canavero!

Transplanting an organ- or body part- from one body into another body is arguably one of medicine’s most intriguing methods of intervention. There have been many cases when a medical doctor attempts to transplant a specific organ into another body to either save somebody’s life, or to help it last a little bit longer. For example, there was a patient who suffered from end-stage systemic right ventricular dysfunction, which basically means the patient’s heart was failing to pump the necessary amount of blood to the body^[1], and was dying. Her doctor performed a heart transplant in 2002, and the patient recovered fairly quickly; in her last checkup in 2005, the doctor reported that she was, “doing well, and fully ambulatory.”^[2] However, one transplant that has never even been attempted, is a full head transplant; until now. Dr. Sergio Canavero believes that he can pull it off, and transplant an entire, fully-functioning human head onto another fully-functioning body with a not-so-functioning head.

This essay will be split into two parts. The first part will explain the procedure and provide reasons why these doctors believe that this is even possible. The second part of this essay will lay out the arguments against the procedure, the arguments for the procedure, and, whether the procedure is a success or a failure, what the procedure will entail for the future of ethics and philosophy. The argument of this essay will ultimately argue for the procedure, and why it can likely be done. Nevertheless, it is best considered as unethical.

I. The Procedure

The Case of Valery Spiridonov

The plausibility of a procedure of this nature to take place in the near future is rapidly becoming more and more likely. This past August, CBS reporter Ashley Welch presented breaking news of the an announcement made by Dr. Sergio Canavero, an Italian neurosurgeon. Dr. Canavero, with help from Dr. Xiaoping Ren, plans to become the first people to successfully undertake and complete a full head transplant.^[3] The man who hopes to find himself on this seemingly fictional operating table is 30 year old Russian computer programmer Valery Spiridonov.^[4] Spiridonov suffers from Werdnig-Hoffman Disease, a very rare genetic disorder which diminishes bone tissue, causes muscular atrophy, and kills off brain cells and spinal cells. Because of his condition, Spiridonov’s fully functional brain is stuck inside a shriveled and dysfunctional body, confined to a wheelchair, and capable only of functionality above the neck as well as hand and arm movement.^[5]

After hearing about Canavero’s work, Spiridonov contacted the Italian doctor in order to volunteer himself. Tired of being unable to care for himself, and of being deprived of many of the pleasures of a functional body, Spiridonov explained, “If I have a chance of full body replacement I will get rid of the limits and be more independent.”^[6] He also added that, “Removing all the sick parts but the head would do a great job in my case … I couldn’t see any other way to treat myself.”^[7] Although Spiridonov’s functionality and capabilities above the neck paired with his optimism and willingness may make him seem like the perfect candidate for this procedure, the whole thing is much more complicated than a simple Dr. Frankenstein cut and paste job. In fact it seems that the amount of detail which would go into the operation is more than we might have ever imagined.

The Proposal

Of course, if the operation were to take place, the attention to detail would be so great and the margin for error so small, that the plan which Dr. Canavero carefully laid out in his proposal would need to be followed precisely.

Canavero explains that they would begin with finding a proper “young brain-dead male patient,” with which to transplant Spiridonov’s head.^[8] The process would start with Spiridonov going under anesthesia and both bodies being lowered to a colder temperature in order to slow the rate of brain cell and spinal cell death caused by the lack of blood flow and oxygen to the head in the absence of connection to a functioning heart and lungs, giving the surgeon’s more time to work.^[9] The surgeon team would then begin to remove both patient’s heads including a spinal cord cut, while simultaneously attaching the blood vessels of Spiridonov’s head to the new body through tubes.

Next, “A custom-made crane would be used to shift Spiridonov’s head – hanging by Velcro straps – onto the donor body’s neck” before Canavero and his team would then begin to reattach the spinal cord using a specially made blend of PEG, or polyethylene glycol, which Dr. Canavero and Dr. Ren have been perfecting through testing of animals in order to better promote the regrowth of spine cells.^[10]^[11] Once the spine is reattached, the next step of the process would be to begin connecting nerves, airways, blood pathways, and muscles. Essentially, anything and everything that needs contact with the brain for its function, or that the brain needs for its own function must be operational and working through the neck area. Once this has been completed, the final touches on the exterior neck area will be finished, and Spiridonov’s new body will be left to recover.

The Time in a Coma

Canavero explains that in order to allow the nerves, muscles, and blood passageways to have the proper time and environment to heal without Spiridonov’s movement hindering or creating new problems, the newly combined body will be left for three-to-four weeks in a comatose state. During this time, Canavero says that the surgeon team would “implant electrodes” in the spinal cord in order to “stimulate” nerves, nerve endings, and muscles to nerve connections in order to prep the body for the consciousness of its operator. If the project is to be approved, Dr. Canavero and Dr. Ren estimate that although the surgery would need around 80 surgeons and would “cost tens of millions of dollars.” Canavero himself even predicted an overwhelmingly confident “90 percent plus” success rate for the transplant.^[12]

Now, of course, this all sounds great in theory. But there is so much more that goes into every aspect of this entire operation than even the step by step process listed above. From every single tiny muscle fiber, to every nerve ending, to every vein and artery, not to mention the reattachment of the spinal cord, the minute detail work required in this surgery is not only overwhelming, but is extremely important to consider if one wants to legitimately understand all that is at stake, and all that must go correctly.

Reflex Arc

The nervous system is perhaps one of the most complicated system in the study of Anatomy. Not only are neurons only connected with a synapse, or gap, between two neurons, but the nerve cells communicate using an electric and chemical factor.^[13] For example, if a person were to step on a nail, then the pain stimulation will start at the afferent sensory neurons in the foot, use different neurotransmitters- acetylcholine, nicotinic cholinergic receptors, adrenergic receptors etc.- to travel up the peripheral nervous system neurons of the leg. Once the pain signal reaches the spinal cord, it crosses over through the dorsal root to travel up to the brain, where the parietal lobe then perceives the signal as pain and sends a signal back down to the foot. However, this time the signal travels down the efferent motor neurons, and crosses over through the ventral root of the spinal cord to travel back down to the foot, telling the foot to jerk back or move.^[14]

Spinal Cord Repair

Now, that paragraph is a rough summary of what happens during a reflex arc of the foot; that was the shortened version. One of the current situations of the nervous system, is that the neurons have very little healing or regeneration on their own if damaged. Neurons actually form cysts, or gliosis at the site of injury if there is any type of tissue damage, blocking regeneration.^[15] That is why there are so many people who are paralyzed are likely paralyzed for life. However, there has been research that points to a way in which the spinal cord can be stimulated with biodegradable polymer scaffolds (which can be compared to a template that can be used for regeneration^[16]), which when coupled with various different growth-promoting cells- like Schwann cells, neural progenitor cells, and mesenchymal stem cells- and growth factors- like GDNF (Glial Cell Derived Neurotrophic Factor, which encodes a gene that makes up a superfamily of protein that stimulates growth)^[17] to bridge the gap of the damage by promoting axonal regeneration.^[18] This method has been tested in different rats and mice, and have been successful.

As mentioned before, Dr. Canavero is planning on using a solution known as polyethylene glycol. Now, the use of PEG 3350 is a laxative, but this is not the same medication being used for the spinal cord repair. PEG has actually been tested, and successful in resealing the axonal membranes of the spinal cord in multiple in vitro and in vivo models. PEG has also shown to decrease the amount of mitochondria-derived oxidative stress on intracellular components. These results point to a theory that PEG can help repair mechanical injury in two different ways: to reseal the plasma membrane, and mitochondrial protection.^[19]

Spinal Cord Fusion

The main problem that Dr. Canavero is facing is the spinal cord fusion. According to a TED Talk at which Dr. Canavero spoke, he states that “spinal cord injury releases 26,000 Newton’s of force. It’s unrecoverable.” He then went on to explain that HEAVEN; “Gemini” (the procedure) will be using an ultra-sharp blade that will only release 10 Newton’s of force. He believes that the spinal cord can be brought back to life using the ultra-sharp blade, coupled with the use of PEG.^[20]

PEG is the key ingredient in this procedure. According to Dr. Canavero, PEG is the “magic” ingredient that can rejoin severed peripheral nerves without the need for “perfect” alignment of the nerve fibers. The first case that PEG was applied to the spinal cord dates back to 1986. He also stated that a group of German doctors severed the spinal cord of a rat, used PEG, and the rat was up and walking around within weeks. Dr. Canavero is convinced that HEAVEN is going to work without a doubt.

This is the procedure, and why Dr. Canavero believes that it will work. However, we can sit and talk about if it will work in theory, but until it happens, we will never know if the patient will survive or not. Now that the possibility question has been answered, an even greater question must be asked. Should this procedure take place? That is the central focus of the second half of this essay.

II. The Ethical Dilemmas of the Procedure

The procedure has caused an uproar in the ethics and medicine field, because a good number of people do not believe the procedure should be done. Even if the procedure seems to be possible, they do not believe that a head transplant is something that humans should be able to do. Stephen Latham, a bioethicist at Yale University is not even convinced that the procedure will work, for he states while laughing in an interview, “If you’d have the technology to attach spinal columns, you’d have certainly developed the technology to repair somebody’s broken spinal column.”^[21] There are a good number of students on campus who would also agree.

However, there are also arguments for the procedure. Dr. Canavero is of course the loudest voice in trying to convince the public that the transplant is ethical, and that there is nothing immoral about the procedure. There are some scientists who would support Dr. Canavero’s claim that there is nothing immoral about the procedure, and that even if we deem it unethical in the present, humans will always move closer and closer to God-like control of health.^[22]

Arguments Against the Procedure

As has been mentioned, the proposal of this first ever head transplant has received a fair amount of negative attention from ethicists, scientists, doctors, and even average citizens alike. From scientific and medical reasoning to ethical understandings of life, and the philosophical understanding of the significance of an individual’s brain, countless people have come forth expressing their disapproval in the operation since Canavero’s initial announcement of intent in early 2015.

It Can Not Be Done

Spinal Difficulties

The first genre of arguments against Dr. Canavero’s work with Spiridonov is the large amount of critique that the operation has received for the legitimacy of the medical science involved. The most specific portion of the operation which seems to garner the most criticism is the reconnection process for the spinal cord. Scientist are arguing that our capability to reattach a spinal cord just simply is not a reality yet. Dr. Eduardo Rodriguez, the doctor behind the world’s most complete facial reconstruction surgery on Richard Norris, is among those in disbelief. After more than 16 years of experience in plastic surgery and spinal research, Rodriguez explains, “I don’t think it’s possible,” and that he does not believe our research is quite there yet. Because we still have yet to find full success refusing the spinal cord of an injured human, Rodriguez tells LiveScience, that combining two separate sections of spinal cord from two completely different individuals only poses a more difficult challenge.

Rodriguez feels that the central nervous system of the human body is far more complicated than Canavero is implying. Even the surgery which Rodriquez and his team completed in 2012 for a retired firefighter and burn victim, although being labelled as the most comprehensive and functional facial transplant surgery done to date, did not restore 100% functionality, feeling, and maneuverability because of the difficulty in restoring nerve connections.^[23]

Organ Preserving

On top of the difficulty of attaching the spinal cord, Dr. Canavero has also caught much controversy in his treatment of the head as a basic organ. Dr. Canavero’s plan for preserving the head after its detachment from the body is to lower its temperature to between 10-15 degrees Celsius, and although this is typical protocol for organs such as kidneys, livers and hearts, according to Business Insider's Erin Brodwin, the head proves to be a much more difficult and complex organ. The head poses all sorts of new issues that have never been fully handled before, including the preservation of “not just the brain, but your eyes, ears, nose, mouth, and skin, as well as two separate gland systems: the pituitary, which controls the hormones that circulate throughout the body, and the salivary, which are responsible for producing saliva.”

This of course is assuming that the head is able to make it to the preservation process. Successfully detaching the head itself is a major endeavor. After decapitation, a major issue that will present itself will be the sudden loss of blood pressure and oxygen rich blood, which because the effects of a lack of oxygen to the brain can be so serious and so quick, this may pose to be a huge obstacle. Another challenge which may prove to be impassible for Dr. Canavero and his team is the battle that the new body will wage against the donor head.

Immune System Complications and Time

When a body comes into contact with a foreign substance, whether that be a bacteria, a virus, a new organ or, in this case, a new head, the body’s immune system will do everything in its power to protect the body from this foreign substance, and although organs are rejected by bodies during and after surgery all of the time, the repercussions of the body rejecting its own head have yet to be seen, but could prove to be fatal for Spiridonov. The icing on the cake for the whole operation, is the fact that Dr. Canavero himself has predicted that he will only have around an hour for the operation to take place.^[24] Even as his history making, and science shattering predictions stood, the odds did not seem to be in Canavero’s favor, however such a small time limit upon such an intricate and precise operation happening in under an hour is one final stipulation which puts the entire procedure outside of the faith and believe a large majority of the science and medical community.^[25]

It Should Not Be Done

The second main argument against the procedure comes from the ethical side of the conversation. One specific person who has really taken it upon himself to interact with and debunk the entire operation for the sake of ethics is bioethicist and New York University professor Arthur Caplan. Caplan exclaims that “I think it's ludicrously stupid, [and you should] ... be charged with homicide if you chop somebody's head off before they're dead.” Another argument that has been used heavily comes from the question of donor versus receiver. Because it is the deceased individual who is contributing more for the operation, the question arises: Who is the donor in this operation and who is the receiver? If Spiridonov is not designated as the receiver, then does this mean that the product will assume the identity of the body, regardless of the consciousness mentality of the person following the surgery.

Many believe that the identity of an individual is heavily based in the physical body of said individual, however this procedure seems to beg for an exception from this.^[26] Along this argument, still others have a hard time accepting that this boundary of personhood is being violated for someone who is not in a critical condition. Spiridonov is not facing life or death, this is simply a fact of the matter. Because of this, many feel that his request for the operation is not one that should be granted. Not only are we using a good healthy body which could have likely gone out in different organs to individuals in more dire need for these parts, but this also has the potential to open up more and more interest in being involved in scientific achievement and scientific history in the future. Granted, the people involved are obviously signing off on the procedures, but is it ethical to allow people to sign themselves up for what is essentially scientific experimentation, if A. it is not necessary to their survival, and B. it becomes a waste of time, money, energy and other resources which could have been spent on patients in critical condition?^[27]

Arguments For the Procedure

Dr. Canavero loves this procedure; one could assume that it is “his baby.” He has been working and planning for this procedure for thirty years, and he believes that there is nothing unethical about it, and he has assembled a team of 150 doctors (80 of them being surgeons) and nurses to back him up. He and Spiridonov agree that there is nothing wrong with heart transplants, and doctors do those every day. Spiridonov went on to say, “I think it's the normal way of technology to evolve. It would be strange to stop at this point when the neurosurgery is ready to take the next step."^[28]

One argument for the procedure is as follows: if the head donor is cognitively willing to participate in the procedure and the body donor’s family willingly gives up custody of their brain-dead patient, then the procedure also has no reason to be refused. The head donor is cognitively willing to participate in the procedure. The only thing that Dr. Canavero is waiting on, is the body donor.^[29] Therefore, contingent on the donation and the acceptance of a body donor, there is no reason the procedure should be refused. This argument is one to which Dr. Canavero and Spiridonov are partial, and a lot of background arguers would agree.

Lack of Arguments For

One of the downfalls of the argument for the procedure, is that there is a substantial lack of articles that argue for the head transplant. This is troubling, and could be due to either the lack of support of the procedure, or the people who do support the procedure are too scared of scrutiny to speak out. This could be a potential problem for other issues as well. If there are topics that people are too afraid of scrutiny that they do not speak out, then the issues cannot be resolved as efficiently as possible. This is likely not the case in this predicament, but there must be enough support behind this procedure for it to be as far along in the process as it is.

III. The Future for Ethics and Philosophy

Regardless of the success or failure of the procedure, there will be a substantial change in the subject of philosophy. One subject in particular is the idea of the “soul.” Famous philosophers such as Plato and Descartes believed that the mind is detached from the body, and is its own separated “body” to phrase it simply. On the other hand, famous philosophers such as Locke, Berkeley, Hume- rejected the idea of the soul, but for still had this view-, and Kant all believed the mind is a part of the brain. Both of these theories will be rocked depending on this procedure. If the procedure is a failure, then we only have to wait until the next, further research is needed to accomplish this feat.

Mind-Body Separation

For example, hypothetically, the procedure is a success, and Spiridonov wakes up in this new body and he has full functionality of his new and improved 2.0 body. However, in this example, Spiridonov wakes up as if he is an animal, and has no human cognition. In this hypothetical situation, it could be argued that the mind of the body and the mind of the head would be fighting over the possession of the whole organism. So then, maybe the rationalists would be correct in their conclusion that the mind is something apart from the body. However, this is an improbable situation, because there has been evidence to back up that the mind is indeed a part of the brain, and philosophers such as William James seemingly agree with this view.^[30]

“Soul-Mind” or Mind just part of the Body

Another hypothetical situation could be this: the procedure is a success, and Spiridonov wakes up in this new body and he has full functionality of his new and improved 2.0 body. However, Spiridonov’s mind works perfectly, and he goes on to live a happy life frolicking through physical therapy and psychological therapy. This situation would point to the conclusion of the empiricists, and occasional rationalists, view that the mind is only a part of the brain.

The Future of Ethics

The future of ethics is also brought into question, and the possibilities that are being brought up. If this surgery is deemed ethical, given that it is successful, the future of the ethics committee of medicine will be forever changed. If a head transplant is granted and successful, then what else will be deemed appropriate? A brain transplant is even more invasive and would have even more of an uproar, because that is taking the “mind” in this example, and putting it in a completely different body. Ethics will forever be changed, because there will be an entirely different mindset when approaching these issues.

Conclusion

After careful analysis of how the procedure is done, and why the doctors believe it will work, the arguments for the procedure, and the arguments against the procedure, one may conclude that the transplantation of a head could be done with current research, even if success is unlikely; but, it should not be attempted. First, the initial cut could potentially kill the patient involved, and then there would be a waste of $10 million and a perfectly healthy body donor. Also, given that if Spiridonov survives the procedure, there is no guarantee that the whole process will be a success. One possibility could be that if Spiridonov wakes up, he could be worse off than he is now. He has control of his hands, so at least he can type. However, there is a possibility that he could not ever regain the ability to move from the neck down at all, and he would be trapped in a body that is not his, and that he cannot move at all.

While the research done with PEG is definitely convincing, it was only effective in re-growing the same spinal cord. There were no studies done on trying to use PEG to rejoin two different spinal cords from two different bodies. If there have not been studies to join two different spinal cords together, then there is a possibility that the surgery could not even be successful. Therefore, there is a possibility that the surgery could not even be successful. There is a possibility that the team of 150 doctors and nurses could be responsible for killing a man who wanted to die; also known as euthanasia. If the reader of this essay would replace “head transplant” with “euthanasia” then there would be a multitude of people against the procedure.^[31]

[1] Hindawi. "Right Ventricular Dysfunction and Failure in Chronic Pressure Overload." Cardiology Research and Practice. Hindawi Publishing Corporation, 23 Mar. 2011. Web. 02 May 2017.

[2] MailOnline, Richard Gray for. "EXCLUSIVE: Doctor planning world's first head transplant says he is preparing for his 'Frankenstein' surgery by REANIMATING human corpses ." Daily Mail Online. Associated Newspapers, 21 Sept. 2016. Web. 02 May 2017.

[3] Welch, Ashley. "Russian man volunteers for first human head transplant." CBS News. CBS Interactive, 29 Aug. 2016. Web. 02 May 2017.

[4] MailOnline, Richard Gray for. "EXCLUSIVE: Doctor planning world's first head transplant says he is preparing for his 'Frankenstein' surgery by REANIMATING human corpses ." Daily Mail Online. Associated Newspapers, 21 Sept. 2016. Web. 02 May 2017.

[5] Welch. Web. 02 May 2017.

[6] "Russian Man Set for World's First Head Transplant." The Telegraph. Telegraph Media Group, 20 Sept. 2016. Web. 02 May 2017.

[7] Welch. Web. 02 May 2017.

[8] Welch. Web. 02 May 2017.

[9] "Russian Man Set for World's First Head Transplant." The Telegraph. Telegraph Media Group, 20 Sept. 2016. Web. 02 May 2017.

[10] Welch. Web. 02 May 2017.

[11] MailOnline, Richard Gray for. "EXCLUSIVE: Doctor planning world's first head transplant says he is preparing for his 'Frankenstein' surgery by REANIMATING human corpses ." Daily Mail Online. Associated Newspapers, 21 Sept. 2016. Web. 02 May 2017.

[12] Welch. Web. 02 May 2017.

[13] Fox, Stuart Ira. Human Physiology. 13th ed. New York: McGraw-Hill, 2013. Print.

[14] O’Mealy, Gary. 12 February 2017. Class Lecture.

[15] "Neuroregeneration - Center for Regenerative Medicine - Mayo Clinic Research." Mayo Clinic. N.p., n.d. Web. 02 May 2017.

[16] Hsu, Shan-hui, Kun-Che Hung, and Cheng-Wei Chen. "Biodegradable polymer scaffolds." Journal of Materials Chemistry B. The Royal Society of Chemistry, 26 Oct. 2016. Web. 02 May 2017.

[17] "GDNF glial cell derived neurotrophic factor [Homo sapiens (human)] - Gene - NCBI." National Center for Biotechnology Information. U.S. National Library of Medicine, 18 Apr. 2017. Web. 02 May 2017.

[18] "Neuroregeneration - Center for Regenerative Medicine - Mayo Clinic Research." Mayo Clinic. N.p., n.d. Web. 02 May 2017.

[19] Shi, R. "Polyethylene glycol repairs membrane damage and enhances functional recovery: a tissue engineering approach to spinal cord injury." Neuroscience bulletin. U.S. National Library of Medicine, 29 Aug. 2013. Web. 02 May 2017.

[20] TEDxTalks. YouTube. YouTube, 18 Sept. 2015. Web. 02 May 2017.

[21] "Would a human head transplant be ethical?" BioCentre. N.p., n.d. Web. 02 May 2017.

[22] Raza, Malika, Hasnain Abbas Dharamshi, Syed Zohaib Ahsan, Zehra Naqvi, Tahira Naqvi, Ali Abbas Mohsin Ali, and Jamaluddin Malik Abbas. "The Future of Ethics in Medicine." Iranian Red Crescent Medical Journal. Kowsar, 18 June 2016. Web. 02 May 2017.

[23] Lewis, Tanya. "Why Head Transplants Won't Happen Any Time Soon."LiveScience. Business Insider Inc., 27 Apr. 2015. Web. 02 May 2017.

[24] MailOnline, Richard Gray for. "EXCLUSIVE: Doctor planning world's first head transplant says he is preparing for his 'Frankenstein' surgery by REANIMATING human corpses ." Daily Mail Online. Associated Newspapers, 21 Sept. 2016. Web. 02 May 2017.

[25] Brodwin, Erin. "In 2017, a surgeon wants to perform the world's first head transplant - here are his biggest obstacles." Business Insider. Business Insider, 27 Apr. 2015. Web. 02 May 2017.

[26] Lewis, Tanya. "Why Head Transplants Won't Happen Any Time Soon."LiveScience. Business Insider Inc., 27 Apr. 2015. Web. 02 May 2017.

[27] "Would a human head transplant be ethical?" BioCentre. N.p., n.d. Web. 02 May 2017.

[28] UK, The Week. "Head transplant: how would it work and is it ethical?" The Week UK. The Week UK, 24 Apr. 2015. Web. 02 May 2017.

[29] UK, The Week. Web. 02 May 2017

[30] Pomerleau, Wayne. "William James (1842—1910)." Internet Encyclopedia of Philosophy. N.p., n.d. Web. 02 May 2017.

[31] Thanks to Logan Luker and Russell Frisbee for content related to this blog post.

Works Cited.

Brodwin, Erin. "In 2017, a surgeon wants to perform the world's first head transplant - here are his biggest obstacles." Business Insider. Business Insider, 27 Apr. 2015. Web. 02 May 2017.

Dittmer, Joel. "Applied Ethics." Internet Encyclopedia of Philosophy. N.p., n.d. Web. 02 May 2017.

Fox, Stuart Ira. Human Physiology. 13th ed. New York: McGraw-Hill, 2013. Print.

"GDNF glial cell derived neurotrophic factor [Homo sapiens (human)] - Gene - NCBI." National Center for Biotechnology Information. U.S. National Library of Medicine, 18 Apr. 2017. Web. 02 May 2017.

Hindawi. "Right Ventricular Dysfunction and Failure in Chronic Pressure Overload." Cardiology Research and Practice. Hindawi Publishing Corporation, 23 Mar. 2011. Web. 02 May 2017.

Hsu, Shan-hui, Kun-Che Hung, and Cheng-Wei Chen. "Biodegradable polymer scaffolds." Journal of Materials Chemistry B. The Royal Society of Chemistry, 26 Oct. 2016. Web. 02 May 2017.

Lewis, Tanya. "Why Head Transplants Won't Happen Any Time Soon."LiveScience. Business Insider Inc., 27 Apr. 2015. Web. 02 May 2017.

MailOnline, Richard Gray for. "EXCLUSIVE: Doctor planning world's first head transplant says he is preparing for his 'Frankenstein' surgery by REANIMATING human corpses." Daily Mail Online. Associated Newspapers, 21 Sept. 2016. Web. 02 May 2017.

Messner, Gregory N., Igor D. Gregoric, Thomas Chu, Branislav Radovancevic, Biswajit Kar, Scott D. Flamm, and O. H. Frazier. "Orthotopic Heart Transplantation in a Patient with D-Transposition of the Great Arteries after a Mustard Procedure." Texas Heart Institute Journal / from the Texas Heart Institute of St. Luke's Episcopal Hospital, Texas Children's Hospital. Published in the Cardiovascular Surgical Research Laboratories, Texas Heart Institute, 2005. Web. 02 May 2017.

"Neuroregeneration - Center for Regenerative Medicine - Mayo Clinic Research." Mayo Clinic. N.p., n.d. Web. 02 May 2017.

O’Mealy, Gary. 12 February 2017. Class Lecture.

Raza, Malika, Hasnain Abbas Dharamshi, Syed Zohaib Ahsan, Zehra Naqvi, Tahira Naqvi, Ali Abbas Mohsin Ali, and Jamaluddin Malik Abbas. "The Future of Ethics in Medicine." Iranian Red Crescent Medical Journal. Kowsar, 18 June 2016. Web. 02 May 2017.

"Russian Man Set for World's First Head Transplant." The Telegraph. Telegraph Media Group, 20 Sept. 2016. Web. 02 May 2017.

Shi, R. "Polyethylene glycol repairs membrane damage and enhances functional recovery: a tissue engineering approach to spinal cord injury." Neuroscience bulletin. U.S. National Library of Medicine, 29 Aug. 2013. Web. 02 May 2017.

TEDxTalks. YouTube. YouTube, 18 Sept. 2015. Web. 02 May 2017.

Toman, Barbara J. "Harnessing the Body's Healing Power." Neuroregenerative Medicine. Mayo Clinic, n.d. Web. 02 May 2017.

UK, The Week. "Head transplant: how would it work and is it ethical?" The Week UK. The Week UK, 24 Apr. 2015. Web. 02 May 2017.

Welch, Ashley. "Russian man volunteers for first human head transplant." CBS News. CBS Interactive, 29 Aug. 2016. Web. 02 May 2017.

Pomerleau, Wayne. "William James (1842—1910)." Internet Encyclopedia of Philosophy. N.p., n.d. Web. 02 May 2017.

ARTIFICIAL INTELLIGENCE AND LIFE IN 2030 (HTML version)

2016-09-04T12:14:00.001-04:00

An easier to use version of an important report on Artificial Intelligence.

A signature panel of experts recently put out a report (in pdf format) titled, "Artificial Intelligence and life in 2030 - a one hundred year study on artificial intelligence." As is too often the case, these reports are locked-up in a propriety, hard to use format -- namely, pdf.

As a response to this problem, I have taken the time to convert this public report to a simple html file so that specialized readers can capture the material for individual use. (I myself use Pocket to verbally read such reports.) I have removed footnotes and references (which can be found in the link above) and made a few other redactions for readability, but I've noted these in the text. I hope others find this html version useful:

* * *

"Artificial Intelligence and life in 2030 - a one hundred year study on artificial intelligence."

PREFACE

The One Hundred Year Study on Artificial Intelligence, launched in the fall of 2014, is a long-term investigation of the field of Artificial Intelligence (AI) and its influences on people, their communities, and society. It considers the science, engineering, and deployment of AI-enabled computing systems. As its core activity, the Standing Committee that oversees the One Hundred Year Study forms a Study Panel every five years to assess the current state of AI. The Study Panel reviews AI’s progress in the years following the immediately prior report, envisions the potential advances that lie ahead, and describes the technical and societal challenges and opportunities these advances raise, including in such arenas as ethics, economics, and the design of systems compatible with human cognition.

The overarching purpose of the One Hundred Year Study’s periodic expert review is to provide a collected and connected set of reflections about AI and its influences as the field advances. The studies are expected to develop syntheses and assessments that provide expert-informed guidance for directions in AI research, development, and systems design, as well as programs and policies to help ensure that these systems broadly benefit individuals and society.1 The One Hundred Year Study is modeled on an earlier effort informally known as the “AAAI Asilomar Study.” During 2008-2009, the then president of the Association for the Advancement of Artificial Intelligence (AAAI), Eric Horvitz, assembled a group of AI experts from multiple institutions and areas of the field, along with scholars of cognitive science, philosophy, and law. Working in distributed subgroups, the participants addressed near-term AI developments, long-term possibilities, and legal and ethical concerns, and then came together in a three-day meeting at Asilomar to share and discuss their findings.

A short written report on the intensive meeting discussions, amplified by the participants’ subsequent discussions with other colleagues, generated widespread interest and debate in the field and beyond. The impact of the Asilomar meeting, and important advances in AI that included AI algorithms and technologies starting to enter daily life around the globe, spurred the idea of a long-term recurring study of AI and its influence on people and society. The One Hundred Year Study was subsequently endowed at a university to enable extended deep thought and cross-disciplinary scholarly investigations that could inspire innovation and provide intelligent advice to government agencies and industry. This report is the first in the planned series of studies that will continue for at least a hundred years. The Standing Committee defined a Study Panel charge for the inaugural Study Panel in the summer of 2015 and recruited Professor Peter Stone, at the University of Texas at Austin, to chair the panel. The seventeen-member Study Panel, comprised of experts in AI from academia, corporate laboratories and industry, and AI-savvy scholars in law, political science, policy, and economics, was launched in mid-fall 2015. The participants represent diverse specialties and geographic regions, genders, and career stages.

The Standing Committee extensively discussed ways to frame the Study Panel charge to consider both recent advances in AI and potential societal impacts on jobs, the environment, transportation, public safety, healthcare, community engagement, and government. The committee considered various ways to focus the study, including surveying subfields and their status, examining a particular technology such as machine learning or natural language processing, and studying particular application areas such as healthcare or transportation. The committee ultimately chose a thematic focus on “AI and Life in 2030” to recognize that AI’s various uses and impacts will not occur independently of one another, or of a multitude of other societal and technological developments. Acknowledging the central role cities have played throughout most of human experience, the focus was narrowed to the large urban areas where most people live. The Standing Committee further narrowed the focus to a typical North American city in recognition of the great variability of urban settings and cultures around the world, and limits on the first Study Panel’s efforts.

The Standing Committee expects that the projections, assessments, and proactive guidance stemming from the study will have broader global relevance and is making plans for future studies to expand the scope of the project internationally As one consequence of the decision to focus on life in North American cities, military applications were deemed to be outside the scope of this initial report. This is not to minimize the importance of careful monitoring and deliberation about the implications of AI advances for defense and warfare, including potentially destabilizing developments and deployments.

The report is designed to address four intended audiences. For the general public, it aims to provide an accessible, scientifically and technologically accurate portrayal of the current state of AI and its potential. For industry, the report describes relevant technologies and legal and ethical challenges, and may help guide resource allocation. The report is also directed to local, national, and international governments to help them better plan for AI in governance. Finally, the report can help AI researchers, as well as their institutions and funders, to set priorities and consider the ethical and legal issues raised by AI research and its applications.

Given the unique nature of the One Hundred Year Study on AI, we expect that future generations of Standing Committees and Study Panels, as well as research scientists, policy experts, leaders in the private and public sectors, and the general public, will reflect on this assessment as they make new assessments of AI’s future. We hope that this first effort in the series stretching out before us will be useful for both its failures and successes in accurately predicting the trajectory and influences of AI. The Standing Committee is grateful to the members of the Study Panel for investing their expertise, perspectives, and significant time to the creation of this inaugural report. We especially thank Professor Peter Stone for agreeing to serve as chair of the study and for his wise, skillful, and dedicated leadership of the panel, its discussions, and creation of the report.

EXECUTIVE SUMMARY

Artificial Intelligence (AI) is a science and a set of computational technologies that are inspired by—but typically operate quite differently from—the ways people use their nervous systems and bodies to sense, learn, reason, and take action. While the rate of progress in AI has been patchy and unpredictable, there have been significant advances since the field’s inception sixty years ago. Once a mostly academic area of study, twenty-first century AI enables a constellation of mainstream technologies that are having a substantial impact on everyday lives. Computer vision and AI planning, for example, drive the video games that are now a bigger entertainment industry than Hollywood. Deep learning, a form of machine learning based on layered representations of variables referred to as neural networks, has made speech-understanding practical on our phones and in our kitchens, and its algorithms can be applied widely to an array of applications that rely on pattern recognition. Natural Language Processing (NLP) and knowledge representation and reasoning have enabled a machine to beat the Jeopardy champion and are bringing new power to Web searches.

While impressive, these technologies are highly tailored to particular tasks. Each application typically requires years of specialized research and careful, unique construction. In similarly targeted applications, substantial increases in the future uses of AI technologies, including more self-driving cars, healthcare diagnostics and targeted treatments, and physical assistance for elder care can be expected. AI and robotics will also be applied across the globe in industries struggling to attract younger workers, such as agriculture, food processing, fulfillment centers, and factories. They will facilitate delivery of online purchases through flying drones, self-driving trucks, or robots that can get up the stairs to the front door.

This report is the first in a series to be issued at regular intervals as a part of the One Hundred Year Study on Artificial Intelligence (AI100). Starting from a charge given by the AI100 Standing Committee to consider the likely influences of AI in a typical North American city by the year 2030, the 2015 Study Panel, comprising experts in AI and other relevant areas focused their attention on eight domains they considered most salient: transportation; service robots; healthcare; education; low-resource communities; public safety and security; employment and workplace; and entertainment. In each of these domains, the report both reflects on progress in the past fifteen years and anticipates developments in the coming fifteen years. Though drawing from a common source of research, each domain reflects different AI influences and challenges, such as the difficulty of creating safe and reliable hardware (transportation and service robots), the difficulty of smoothly interacting with human experts (healthcare and education), the challenge of gaining public trust (low-resource communities and public safety and security), the challenge of overcoming fears of marginalizing humans (employment and workplace), and the social and societal risk of diminishing interpersonal interactions (entertainment). The report begins with a reflection on what constitutes Artificial Intelligence, and concludes with recommendations concerning AI-related policy. These recommendations include accruing technical expertise about AI in government and devoting more resources—and removing impediments—to research on the fairness, security, privacy, and societal impacts of AI systems.

Contrary to the more fantastic predictions for AI in the popular press, the Study Panel found no cause for concern that AI is an imminent threat to humankind. No machines with self-sustaining long-term goals and intent have been developed, nor are they likely to be developed in the near future. Instead, increasingly useful applications of AI, with potentially profound positive impacts on our society and economy are likely to emerge between now and 2030, the period this report considers.

At the same time, many of these developments will spur disruptions in how human labor is augmented or replaced by AI, creating new challenges for the economy and society more broadly. Application design and policy decisions made in the near term are likely to have long-lasting influences on the nature and directions of such developments, making it important for AI researchers, developers, social scientists, and policymakers to balance the imperative to innovate with mechanisms to ensure that AI’s economic and social benefits are broadly shared across society. If society approaches these technologies primarily with fear and suspicion, missteps that slow AI’s development or drive it underground will result, impeding important work on ensuring the safety and reliability of AI technologies. On the other hand, if society approaches AI with a more open mind, the technologies emerging from the field could profoundly transform society for the better in the coming decades.

OVERVIEW

The frightening, futurist portrayals of Artificial Intelligence that dominate films and novels, and shape the popular imagination, are fictional. In reality, AI is already changing our daily lives, almost entirely in ways that improve human health, safety, and productivity. Unlike in the movies, there is no race of superhuman robots on the horizon or probably even possible. And while the potential to abuse AI technologies must be acknowledged and addressed, their greater potential is, among other things, to make driving safer, help children learn, and extend and enhance people’s lives. In fact, beneficial AI applications in schools, homes, and hospitals are already growing at an accelerated pace. Major research universities devote departments to AI studies, and technology companies such as Apple, Facebook, Google, IBM, and Microsoft spend heavily to explore AI applications they regard as critical to their futures.

Even Hollywood uses AI technologies to bring its dystopian AI fantasies to the screen. Innovations relying on computer-based vision, speech recognition, and Natural Language Processing have driven these changes, as have concurrent scientific and technological advances in related fields. AI is also changing how people interact with technology. Many people have already grown accustomed to touching and talking to their smart phones. People’s future relationships with machines will become ever more nuanced, fluid, and personalized as AI systems learn to adapt to individual personalities and goals. These AI applications will help monitor people’s well-being, alert them to risks ahead, and deliver services when needed or wanted. For example, in a mere fifteen years in a typical North American city—the time frame and scope of this report— AI applications are likely to transform transportation toward self-driving vehicles with on-time pickup and delivery of people and packages. This alone will reconfigure the urban landscape, as traffic jams and parking challenges become obsolete.

This study’s focus on a typical North American city is deliberate and meant to highlight specific changes affecting the everyday lives of the millions of people who inhabit them. The Study Panel further narrowed its inquiry to eight domains where AI is already having or is projected to have the greatest impact: transportation, healthcare, education, low-resource communities, public safety and security, employment and workplace, home/service robots, and entertainment.

Though drawing from a common source of research, AI technologies have influenced and will continue to influence these domains differently. Each domain faces varied AI-related challenges, including the difficulty of creating safe and reliable hardware for sensing and effecting (transportation and service robots), the difficulty of smoothly interacting with human experts (healthcare and education), the challenge of gaining public trust (low-resource communities and public safety and security), the challenge of overcoming fears of marginalizing humans (employment and workplace) and the risk of diminishing interpersonal interaction (entertainment). Some domains are primarily business sectors, such as transportation and healthcare, while others are more oriented to consumers, such as entertainment and home service robots. Some cut across sectors, such as employment/workplace and low-resource communities.

In each domain, even as AI continues to deliver important benefits, it also raises important ethical and social issues, including privacy concerns. Robots and other AI technologies have already begun to displace jobs in some sectors. As a society, we are now at a crucial juncture in determining how to deploy AI-based technologies in ways that promote, not hinder, democratic values such as freedom, equality, and transparency. For individuals, the quality of the lives we lead and how our contributions are valued are likely to shift gradually, but markedly. Over the next several years, AI research, systems development, and social and regulatory frameworks will shape how the benefits of AI are weighed against its costs and risks, and how broadly these benefits are spread.

An accurate and sophisticated picture of AI—one that competes with its popular portrayal—is hampered at the start by the difficulty of pinning down a precise definition of artificial intelligence. In the approaches the Study Panel considered, none suggest there is currently a “general purpose” AI. While drawing on common research and technologies, AI systems are specialized to accomplish particular tasks, and each application requires years of focused research and a careful, unique construction. As a result, progress is uneven within and among the eight domains.

A prime example is Transportation, where a few key technologies have catalyzed the widespread adoption of AI with astonishing speed. Autonomous transportation will soon be commonplace and, as most people’s first experience with physically embodied AI systems, will strongly influence the public’s perception of AI. As cars become better drivers than people, city-dwellers will own fewer cars, live further from work, and spend time differently, leading to an entirely new urban organization. In the typical North American city in 2030, physically embodied AI applications will not be limited to cars, but are likely to include trucks, flying vehicles, and personal robots. Improvements in safe and reliable hardware will spur innovation over the next fifteen years, as they will with Home/Service Robots, which have already entered people’s houses, primarily in the form of vacuum cleaners. Better chips, low-cost 3D sensors, cloud-based machine learning, and advances in speech understanding will enhance future robots’ services and their interactions with people. Special purpose robots will deliver packages, clean offices, and enhance security. But technical constraints and the high costs of reliable mechanical devices will continue to limit commercial opportunities to narrowly defined applications for the foreseeable future.

In Healthcare, there has been an immense forward leap in collecting useful data from personal monitoring devices and mobile apps, from electronic health records (EHR) in clinical settings and, to a lesser extent, from surgical robots designed to assist with medical procedures and service robots supporting hospital operations. AI-based applications could improve health outcomes and the quality of life for millions of people in the coming years. Though clinical applications have been slow to move from the computer science lab to the real-world, there are hopeful signs that the pace of innovation will improve. Advances in healthcare can be promoted via the development of incentives and mechanisms for sharing data and for removing overbearing policy, regulatory, and commercial obstacles. For many applications, AI systems will have to work closely with care providers and patients to gain their trust. Advances in how intelligent machines interact naturally with caregivers, patients, and patients’ families are crucial.

Enabling more fluid interactions between people and promising AI technologies also remains a critical challenge in Education, which has seen considerable progress in the same period. Though quality education will always require active engagement by human teachers, AI promises to enhance education at all levels, especially by providing personalization at scale. Interactive machine tutors are now being matched to students for teaching science, math, language, and other disciplines. Natural Language Processing, machine learning, and crowdsourcing have boosted online learning and enabled teachers in higher education to multiply the size of their classrooms while addressing individual students’ learning needs and styles. Over the next fifteen years in a typical North American city, the use of these technologies in the classroom and in the home is likely to expand significantly, provided they can be meaningfully integrated with face-to-face learning.

Beyond education, many opportunities exist for AI methods to assist Low-resource Communities by providing mitigations and solutions to a variety of social problems. Traditionally, funders have underinvested in AI research lacking commercial application. With targeted incentives and funding priorities, AI technologies could help address the needs of low-resource communities, and budding efforts are promising. Using data mining and machine learning, for example, AI has been used to create predictive models to help government agencies address issues such as prevention of lead poisoning in at-risk children and distribution of food efficiently. These budding efforts suggest more could be done, particularly if agencies and organizations can engage and build trust with these communities. Gaining public trust is also a challenge for AI use by Public Safety and Security professionals. North American cities and federal agencies have already begun to deploy AI technologies in border administration and law enforcement. By 2030, they will rely heavily upon them, including improved cameras and drones for surveillance, algorithms to detect financial fraud, and predictive policing. The latter raises the specter of innocent people being unjustifiably monitored, and care must be taken to avoid systematizing human bias and to protect civil liberties. Well-deployed AI prediction tools have the potential to provide new kinds of transparency about data and inferences, and may be applied to detect, remove, or reduce human bias, rather than reinforcing it.

Social and political decisions are likewise at play in AI’s influences on Employment and Workplace trends, such as the safety nets needed to protect people from structural changes in the economy. AI is poised to replace people in certain kinds of jobs, such as in the driving of taxis and trucks. However, in many realms, AI will likely replace tasks rather than jobs in the near term, and will also create new kinds of jobs. But the new jobs that will emerge are harder to imagine in advance than the existing jobs that will likely be lost. AI will also lower the cost of many goods and services, effectively making everyone better off. Longer term, AI may be thought of as a radically different mechanism for wealth creation in which everyone should be entitled to a portion of the world’s AI-produced treasures. It is not too soon for social debate on how the economic fruits of AI technologies should be shared.

Entertainment has been transformed by social networks and other platforms for sharing and browsing blogs, videos, and photos, which rely on techniques actively developed in NLP, information retrieval, image processing, crowdsourcing, and machine learning. Some traditional sources of entertainment have also embraced AI to compose music, create stage performances, and even to generate 3D scenes from natural language text. The enthusiasm with which people have already responded to AI-driven entertainment has been surprising. As with many aspects of AI, there is ongoing debate about the extent to which the technology replaces or enhances sociability. AI will increasingly enable entertainment that is more interactive, personalized, and engaging. Research should be directed toward understanding how to leverage these attributes for individuals’ and society’s benefit.

What’s next for AI research?

The research that fuels the AI revolution has also seen rapid changes. Foremost among them is the maturation of machine learning, stimulated in part by the rise of the digital economy, which both provides and leverages large amounts of data. Other factors include the rise of cloud computing resources and consumer demand for widespread access to services such as speech recognition and navigation support. Machine learning has been propelled dramatically forward by impressive empirical successes of artificial neural networks, which can now be trained with huge data sets and large-scale computing. This approach has been come to be known as “deep learning.” The leap in the performance of information processing algorithms has been accompanied by significant progress in hardware technology for basic operations such as sensing, perception, and object recognition. New platforms and markets for data-driven products, and the economic incentives to find new products and markets, have also stimulated research advances. Now, as it becomes a central force in society, the field of AI is shifting toward building intelligent systems that can collaborate effectively with people, and that are more generally human-aware, including creative ways to develop interactive and scalable ways for people to teach robots. These trends drive the currently “hot” areas of AI research into both fundamental methods and application areas:

Large-scale machine learning concerns the design of learning algorithms, as well as scaling existing algorithms, to work with extremely large data sets. Deep learning, a class of learning procedures, has facilitated object recognition in images, video labeling, and activity recognition, and is making significant inroads into other areas of perception, such as audio, speech, and natural language processing. Reinforcement learning is a framework that shifts the focus of machine learning from pattern recognition to experience-driven sequential decision-making. It promises to carry AI applications forward toward taking actions in the real world. While largely confined to academia over the past several decades, it is now seeing some practical, real-world successes.

Robotics is currently concerned with how to train a robot to interact with the world around it in generalizable and predictable ways, how to facilitate manipulation of objects in interactive environments, and how to interact with people. Advances in robotics will rely on commensurate advances to improve the reliability and generality of computer vision and other forms of machine perception.

Computer vision is currently the most prominent form of machine perception. It has been the sub-area of AI most transformed by the rise of deep learning. For the first time, computers are able to perform some vision tasks better than people. Much current research is focused on automatic image and video captioning.

Natural Language Processing, often coupled with automatic speech recognition, is quickly becoming a commodity for widely spoken languages with large data sets. Research is now shifting to develop refined and capable systems that are able to interact with people through dialog, not just react to stylized requests. Great strides have also been made in machine translation among different languages, with more real-time person-to-person exchanges on the near horizon.

Collaborative systems research investigates models and algorithms to help develop autonomous systems that can work collaboratively with other systems and with humans. Crowdsourcing and human computation research investigates methods to augment computer systems by making automated calls to human expertise to solve problems that computers alone cannot solve well.

Algorithmic game theory and computational social choice draw attention to the economic and social computing dimensions of AI, such as how systems can handle potentially misaligned incentives, including self-interested human participants or firms and the automated AI-based agents representing them.

Internet of Things (IoT) research is devoted to the idea that a wide array of devices, including appliances, vehicles, buildings, and cameras, can be interconnected to collect and share their abundant sensory information to use for intelligent purposes. Neuromorphic computing is a set of technologies that seek to mimic

biological neural networks to improve the hardware efficiency and robustness of computing systems, often replacing an older emphasis on separate modules for input/ output, instruction-processing, and memory.

AI policy, now and in the future

The measure of success for AI applications is the value they create for human lives. In that light, they should be designed to enable people to understand AI systems successfully, participate in their use, and build their trust. Public policies should help ease society’s adaptation to AI applications, extend their benefits, and mitigate their inevitable errors and failures. Debate about how AI is deployed, including concerns about how privacy is protected and AI’s benefits fairly shared, should be encouraged. Given the speed with which AI technologies are being realized, and concomitant concerns about their implications, the Study Panel recommends that all layers of government acquire technical expertise in AI. Further, research on the fairness, security, privacy, and societal implications of AI systems should be encouraged by removing impediments and increasing private and public spending to support it.

Currently in the United States, at least sixteen separate agencies govern sectors of the economy related to AI technologies. Rapid advances in AI research and, especially, its applications require experts in these sectors to develop new concepts and metaphors for law and policy. Who is responsible when a self-driven car crashes or an intelligent medical device fails? How can AI applications be prevented from promulgating racial discrimination or financial cheating? Who should reap the gains of efficiencies enabled by AI technologies and what protections should be afforded to people whose skills are rendered obsolete? As people integrate AI more broadly and deeply into industrial processes and consumer products, best practices need to be spread, and regulatory regimes adapted.

While the Study Panel does not consider it likely that near-term AI systems will autonomously choose to inflict harm on people, it will be possible for people to use AI-based systems for harmful as well as helpful purposes. And though AI algorithms may be capable of making less biased decisions than a typical person, it remains a deep technical challenge to ensure that the data that inform AI-based decisions can be kept free from biases that could lead to discrimination based on race, sexual orientation, or other factors.

Faced with the profound changes that AI technologies can produce, pressure for “more” and “tougher” regulation is probably inevitable. Misunderstandings about what AI is and is not could fuel opposition to technologies with the potential to benefit everyone. Inappropriate regulatory activity would be a tragic mistake. Poorly informed regulation that stifles innovation, or relocates it to other jurisdictions, would be counterproductive.

Fortunately, principles that guide successful regulation of current digital technologies provide a starting point. In privacy regulation, broad legal mandates coupled with tough transparency requirements and meaningful enforcement—rather than strict controls—encourage companies to develop processes and professional staff to enforce privacy controls, engage with outside stakeholders, and adapt their practices to technological advances. This in turn supports the development of professional trade associations and standards committees that spread best practices. In AI, too, regulators can strengthen a virtuous cycle of activity involving internal and external accountability, transparency, and professionalization, rather than narrow compliance.

A vigorous and informed debate about how to best steer AI in ways that enrich our lives and our society, while encouraging creativity in the field, is an urgent and vital need. AI technologies could widen existing inequalities of opportunity if access to them—along with the high-powered computation and large-scale data that fuel many of them—is unfairly distributed across society. These technologies will improve the abilities and efficiency of people who have access to them. Policies should be evaluated as to whether they foster democratic values and equitable sharing of AI’s benefits, or concentrate power and benefits in the hands of a fortunate few.

As this report documents, significant AI-related advances have already had an impact on North American cities over the past fifteen years, and even more substantial developments will occur over the next fifteen. Recent advances are largely due to the growth and analysis of large data sets enabled by the internet, advances in sensory technologies and, more recently, applications of “deep learning.” In the coming years, as the public encounters new AI applications in domains such as transportation and healthcare, they must be introduced in ways that build trust and understanding, and respect human and civil rights. While encouraging innovation, policies and processes should address ethical, privacy, and security implications, and should work to ensure that the benefits of AI technologies will be spread broadly and fairly. Doing so will be critical if Artificial Intelligence research and its applications are to exert a positive influence on North American urban life in 2030 and beyond.

SECTION I: WHAT IS ARTIFICIALINTELLIGENCE? This section describes how researchers and practitioners define “Artificial Intelligence,” and the areas of AI research and application that are currently thriving. It proffers definitions of what AI is and is not, and describes some of the currently “hot” areas of AI Research. This section lays the groundwork for Section II, which elaborates on AI’s impacts and future in eight domains and Section III, which describes issues related to AI design and public policy and makes recommendations for encouraging AI innovation while protecting democratic values. Note: some of this section was skipped, since this information is already well known.

AI RESEARCH TRENDS

Until the turn of the millennium, AI’s appeal lay largely in its promise to deliver, but in the last fifteen years, much of that promise has been redeemed. AI technologies already pervade our lives. As they becomes a central force in society, the field is shifting from simply building systems that are intelligent to building intelligent systems that are human-aware and trustworthy.

Several factors have fueled the AI revolution. Foremost among them is the maturing of machine learning, supported in part by cloud computing resources and wide-spread, web-based data gathering. Machine learning has been propelled dramatically forward by “deep learning,” a form of adaptive artificial neural networks trained using a method called backpropagation. This leap in the performance of information processing algorithms has been accompanied by significant progress in hardware technology for basic operations such as sensing, perception, and object recognition. New platforms and markets for data-driven products, and the economic incentives to find new products and markets, have also contributed to the advent of AI-driven technology.

All these trends drive the “hot” areas of research described below. This compilation is meant simply to reflect the areas that, by one metric or another, currently receive greater attention than others. They are not necessarily more important or valuable than other ones. Indeed, some of the currently “hot” areas were less popular in past years, and it is likely that other areas will similarly re-emerge in the future. Large-scale machine learning

Many of the basic problems in machine learning (such as supervised and unsupervised learning) are well-understood. A major focus of current efforts is to scale existing algorithms to work with extremely large data sets. For example, whereas traditional methods could afford to make several passes over the data set, modern ones are designed to make only a single pass; in some cases, only sublinear methods (those that only look at a fraction of the data) can be admitted.

Deep learning

The ability to successfully train convolutional neural networks has most benefited the field of computer vision, with applications such as object recognition, video labeling, activity recognition, and several variants thereof. Deep learning is also making significant inroads into other areas of perception, such as audio, speech, and natural language processing.

Reinforcement learning

Whereas traditional machine learning has mostly focused on pattern mining, reinforcement learning shifts the focus to decision making, and is a technology that will help AI to advance more deeply into the realm of learning about and executing actions in the real world. It has existed for several decades as a framework for experience-driven sequential decision-making, but the methods have not found great success in practice, mainly owing to issues of representation and scaling. However, the advent of deep learning has provided reinforcement learning with a “shot in the arm.” The recent success of AlphaGo, a computer program developed by Google Deepmind that beat the human Go champion in a five-game match, was due in large part to reinforcement learning. AlphaGo was trained by initializing an automated agent with a human expert database, but was subsequently refined by playing a large number of games against itself and applying reinforcement learning.

Robotics

Robotic navigation, at least in static environments, is largely solved. Current efforts consider how to train a robot to interact with the world around it in generalizable and predictable ways. A natural requirement that arises in interactive environments is manipulation, another topic of current interest. The deep learning revolution is only beginning to influence robotics, in large part because it is far more difficult to acquire the large labeled data sets that have driven other learning-based areas of AI. Reinforcement learning (see above), which obviates the requirement of labeled data, may help bridge this gap but requires systems to be able to safely explore a policy space without committing errors that harm the system itself or others. Advances in reliable machine perception, including computer vision, force, and tactile perception, much of which will be driven by machine learning, will continue to be key enablers to advancing the capabilities of robotics.

Computer vision

Computer vision is currently the most prominent form of machine perception. It has been the sub-area of AI most transformed by the rise of deep learning. Until just a few years ago, support vector machines were the method of choice for most visual classification tasks. But the confluence of large-scale computing, especially on GPUs, the availability of large datasets, especially via the internet, and refinements of neural network algorithms has led to dramatic improvements in performance on benchmark tasks (e.g., classification on ImageNet). For the first time, computers are able to perform some (narrowly defined) visual classification tasks better than people. Much current research is focused on automatic image and video captioning.

Natural Language Processing

Often coupled with automatic speech recognition, Natural Language Processing is another very active area of machine perception. It is quickly becoming a commodity for mainstream languages with large data sets. Google announced that 20% of current mobile queries are done by voice, and recent demonstrations have proven the possibility of real-time translation. Research is now shifting towards developing refined and capable systems that are able to interact with people through dialog, not just react to stylized requests.

Collaborative systems

Research on collaborative systems investigates models and algorithms to help develop autonomous systems that can work collaboratively with other systems and with humans. This research relies on developing formal models of collaboration, and studies the capabilities needed for systems to become effective partners. There is growing interest in applications that can utilize the complementary strengths of humans and machines—for humans to help AI systems to overcome their limitations, and for agents to augment human abilities and activities.

Crowdsourcing and human computation

Since human abilities are superior to automated methods for accomplishing many tasks, research on crowdsourcing and human computation investigates methods to augment computer systems by utilizing human intelligence to solve problems that computers alone cannot solve well. Introduced only about fifteen years ago, this research now has an established presence in AI. The best-known example of crowdsourcing is Wikipedia, a knowledge repository that is maintained and updated by netizens and that far exceeds traditionally-compiled information sources, such as encyclopedias and dictionaries, in scale and depth. Crowdsourcing focuses on devising innovative ways to harness human intelligence. Citizen science platforms energize volunteers to solve scientific problems, while paid crowdsourcing platforms such as Amazon Mechanical Turk provide automated access to human intelligence on demand. Work in this area has facilitated advances in other subfields of AI, including computer vision and NLP, by enabling large amounts of labeled training data and/or human interaction data to be collected in a short amount of time. Current research efforts explore ideal divisions of tasks between humans and machines based on their differing capabilities and costs.

Algorithmic game theory and computational social choice

New attention is being drawn to the economic and social computing dimensions of AI, including incentive structures. Distributed AI and multi-agent systems have been studied since the early 1980s, gained prominence starting in the late 1990s, and were accelerated by the internet. A natural requirement is that systems handle potentially misaligned incentives, including self-interested human participants or firms, as well as automated AI-based agents representing them. Topics receiving attention include computational mechanism design (an economic theory of incentive design, seeking incentive-compatible systems where inputs are truthfully reported), computational social choice (a theory for how to aggregate rank orders on alternatives), incentive aligned information elicitation (prediction markets, scoring rules, peer prediction) and algorithmic game theory (the equilibria of markets, network games, and parlor games such as Poker—a game where significant advances have been made in recent years through abstraction techniques and no-regret learning).

Internet of Things (IoT)

A growing body of research is devoted to the idea that a wide array of devices can be interconnected to collect and share their sensory information. Such devices can include appliances, vehicles, buildings, cameras, and other things. While it’s a matter of technology and wireless networking to connect the devices, AI can process and use the resulting huge amounts of data for intelligent and useful purposes. Currently, these devices use a bewildering array of incompatible communication protocols. AI could help tame this Tower of Babel.

Neuromorphic Computing

Traditional computers implement the von Neumann model of computing, which separates the modules for input/output, instruction-processing, and memory. With the success of deep neural networks on a wide array of tasks, manufacturers are actively pursuing alternative models of computing—especially those that are inspired by what is known about biological neural networks—with the aim of improving the hardware efficiency and robustness of computing systems. At the moment, such “neuromorphic” computers have not yet clearly demonstrated big wins, and are just beginning to become commercially viable. But it is possible that they will become commonplace (even if only as additions to their von Neumann cousins) in the near future. Deep neural networks have already created a splash in the application landscape. A larger wave may hit when these networks can be trained and executed on dedicated neuromorphic hardware, as opposed to simulated on standard von Neumann architectures, as they are today.

Overall trends and the future of AI research

The resounding success of the data-driven paradigm has displaced the traditional paradigms of AI. Procedures such as theorem proving and logic-based knowledge representation and reasoning are receiving reduced attention, in part because of the ongoing challenge of connecting with real-world groundings. Planning, which was a mainstay of AI research in the seventies and eighties, has also received less attention of late due in part to its strong reliance on modeling assumptions that are hard to satisfy in realistic applications. Model-based approaches—such as physics-based approaches to vision and traditional control and mapping in robotics—have by and large given way to data-driven approaches that close the loop with sensing the results of actions in the task at hand. Bayesian reasoning and graphical models, which were very popular even quite recently, also appear to be going out of favor, having been drowned by the deluge of data and the remarkable success of deep learning. Over the next fifteen years, the Study Panel expects an increasing focus on developing systems that are human-aware, meaning that they specifically model, and are specifically designed for, the characteristics of the people with whom they are meant to interact. There is a lot of interest in trying to find new, creative ways to develop interactive and scalable ways to teach robots. Also, IoT-type systems— devices and the cloud—are becoming increasingly popular, as is thinking about social and economic dimensions of AI. In the coming years, new perception/object recognition capabilities and robotic platforms that are human-safe will grow, as will data-driven products and their markets.

The Study Panel also expects a reemergence of some of the traditional forms of AI as practitioners come to realize the inevitable limitations of purely end-to-end deep learning approaches. We encourage young researchers not to reinvent the wheel, but rather to maintain an awareness of the significant progress in many areas of AI during the first fifty years of the field, and in related fields such as control theory, cognitive science, and psychology

SECTION II: AI BY DOMAIN

Though different instances of AI research and practice share common technologies, such as machine learning, they also vary considerably in different sectors of the economy and society. We call these sectors “domains,” and in this section describe the different states of AI research and implementation, as well as impacts and distinct challenges, in eight of them: transportation; home/service robotics; healthcare; education; low-resource communities; public safety and security; employment and workplace; and entertainment. Based on these analyses, we also predict trends in a typical North American city over the next fifteen years. Contrary to AI’s typical depiction in popular culture, we seek to offer a balanced overview of the ways in which AI is already beginning to transform everyday life, and how those transformations are likely to grow by the year 2030.

TRANSPORTATION

Transportation is likely to be one of the first domains in which the general public will be asked to trust the reliability and safety of an AI system for a critical task. Autonomous transportation will soon be commonplace and, as most people’s first experience with physically embodied AI systems, will strongly influence the public’s perception of AI. Once the physical hardware is made sufficiently safe and robust, its introduction to daily life may happen so suddenly as to surprise the public, which will require time to adjust. As cars will become better drivers than people, city-dwellers will own fewer cars, live further from work, and spend time differently, leading to an entirely new urban organization. Further, in the typical North American city in 2030, changes won’t be limited to cars and trucks, but are likely to include flying vehicles and personal robots, and will raise social, ethical and policy issues. A few key technologies have already catalyzed the widespread adoption of AI in transportation. Compared to 2000, the scale and diversity of data about personal and population-level transportation available today—enabled by the adoption of smartphones and decreased costs and improved accuracies for variety of sensors—is astounding. Without the availability of this data and connectivity, applications such as real-time sensing and prediction of traffic, route calculations, peer-to-peer ridesharing and self-driving cars would not be possible.

Smarter cars

GPS was introduced to personal vehicles in 2001 with in-car navigation devices and has since become a fundamental part of the transportation infrastructure. GPS assists drivers while providing large-scale information to technology companies and cities about transportation patterns. Widespread adoption of smartphones with GPS technology further increased connectivity and the amount of location data shared by individuals.

Current vehicles are also equipped with a wide range of sensing capabilities. An average automobile in the US is predicted to have seventy sensors including gyroscopes, accelerometers, ambient light sensors, and moisture sensors. Sensors are not new to vehicles. Automobiles built before 2000 had sensors for the internal state of the vehicle such as its speed, acceleration, and wheel position. Self-driving vehicles

Since the 1930s, science fiction writers dreamed of a future with self-driving cars, and building them has been a challenge for the AI community since the 1960s. By the 2000s, the dream of autonomous vehicles became a reality in the sea and sky, and even on Mars, but self-driving cars existed only as research prototypes in labs. Driving in a city was considered to be a problem too complex for automation due to factors like pedestrians, heavy traffic, and the many unexpected events that can happen outside of the car’s control. Although the technological components required to make such autonomous driving possible were available in 2000—and indeed some autonomous car prototypes existed —few predicted that mainstream companies would be developing and deploying autonomous cars by 2015. During the first Defense Advanced Research Projects Agency (DARPA) “grand challenge” on autonomous driving in 2004, research teams failed to complete the challenge in a limited desert setting.

But in eight short years, from 2004-2012, speedy and surprising progress occurred in both academia and industry. Advances in sensing technology and machine learning for perception tasks has sped progress and, as a result, Google’s autonomous vehicles and Tesla’s semi-autonomous cars are driving on city streets today. Google’s selfdriving cars, which have logged more than 1,500,000 miles (300,000 miles without an accident), are completely autonomous—no human input needed. Tesla has widely released self-driving capability to existing cars with a software update. Their cars are semi-autonomous, with human drivers expected to stay engaged and take over if they detect a potential problem. It is not yet clear whether this semi-autonomous approach is sustainable, since as people become more confident in the cars’ capabilities, they are likely to pay less attention to the road, and become less reliable when they are most needed. The first traffic fatality involving an autonomous car, which occurred in June of 2016, brought this question into sharper focus.

In the near future, sensing algorithms will achieve super-human performance for capabilities required for driving. Automated perception, including vision, is already near or at human-level performance for well-defined tasks such as recognition and tracking. Advances in perception will be followed by algorithmic improvements in higher level reasoning capabilities such as planning. A recent report predicts self-driving cars to be widely adopted by 2020. And the adoption of self-driving capabilities won’t be limited to personal transportation. We will see self-driving and remotely controlled delivery vehicles, flying vehicles, and trucks. Peer-to-peer transportation services such as ridesharing are also likely to utilize self-driving vehicles. Beyond self-driving cars, advances in robotics will facilitate the creation and adoption of other types of autonomous vehicles, including robots and drones.

It is not yet clear how much better self-driving cars need to become to encourage broad acceptance. The collaboration required in semi-self-driving cars and its implications for the cognitive load of human drivers is not well understood. But if future self-driving cars are adopted with the predicted speed, and they exceed human-level performance in driving, other significant societal changes will follow. Self-driving cars will eliminate one of the biggest causes of accidental death and injury in United States, and lengthen people’s life expectancy. On average, a commuter in US spends twenty-five minutes driving each way.37 With self-driving car technology, people will have more time to work or entertain themselves during their commutes. And the increased comfort and decreased cognitive load with self-driving cars and shared transportation may affect where people choose to live. The reduced need for parking may affect the way cities and public spaces are designed. Self-driving cars may also serve to increase the freedom and mobility of different subgroups of the population, including youth, elderly and disabled.

Self-driving cars and peer-to-peer transportation services may eliminate the need to own a vehicle. The effect on total car use is hard to predict. Trips of empty vehicles and people’s increased willingness to travel may lead to more total miles driven. Alternatively, shared autonomous vehicles—people using cars as a service rather than owning their own—may reduce total miles, especially if combined with well-constructed incentives, such as tolls or discounts, to spread out travel demand, share trips, and reduce congestion. The availability of shared transportation may displace the need for public transportation—or public transportation may change form towards personal rapid transit, already available in four cities,which uses small capacity vehicles to transport people on demand and point-to-point between many stations.

As autonomous vehicles become more widespread, questions will arise over their security, including how to ensure that technologies are safe and properly tested under different road conditions prior to their release. Autonomous vehicles and the connected transportation infrastructure will create a new venue for hackers to exploit vulnerabilities to attack. Ethical questions are also involved in programming cars to act in situations in which human injury or death is inevitable, especially when there are split-second choices to be made about whom to put at risk. The legal systems in most states in the US do not have rules covering self-driving cars. As of 2016, four states in the US (Nevada, Florida, California, and Michigan), Ontario in Canada, the United Kingdom, France, and Switzerland have passed rules for the testing of self-driving cars on public roads. Even these laws do not address issues about responsibility and assignment of blame for an accident for self-driving and semi-selfdriving cars.

Transportation planning

By 2005, cities had started investing in the transportation infrastructure to develop sensing capabilities for vehicle and pedestrian traffic.The sensors currently used include inductive loops, video cameras, remote traffic microwave sensors, radars, and GPS. For example, in 2013 New York started using a combination of microwave sensors, a network of cameras, and pass readers to detect vehicle traffic in the city. Cities use AI methods to optimize services in several ways, such as bus and subway schedules, and tracking traffic conditions to dynamically adjust speed limits or apply smart pricing on highways, bridges, and HOV lanes. Using sensors and cameras in the road network, they can also optimize traffic light timing for improving traffic flow and to help with automated enforcement. These dynamic strategies are aimed at better utilizing the limited resources in the transportation network, and are made possible by the availability of data and the widespread connectivity of individuals. Before the 2000s, transportation planners were forced to rely on static pricing strategies tied to particular days or times of day, to manage demand. As dynamic pricing strategies are adopted, this raises new issues concerning the fair distribution of public goods, since market conditions in high-demand situations may make services unavailable to segments of the public.

The availability of large-scale data has also made transportation an ideal domain for machine learning applications. Since 2006, applications such as Mapquest, Google Maps, and Bing Maps have been widely used by the public for routing trips, using public transportation, receiving real-time information and predictions about traffic conditions, and finding services around a location.Optimal search algorithms have been applied to the routing of vehicles and pedestrians to a given destination (i.e.,). Despite these advances, the widespread application of sensing and optimization techniques to city infrastructure has been slower than the application of these techniques to individual vehicles or people. Although individual cities have implemented sensing and optimization applications, as yet there is no standardization of the sensing infrastructure and AI techniques used. Infrastructure costs, differing priorities among cities, and the high coordination costs among the parties involved have slowed adoption, as have public concerns over privacy related to sensing. Still, AI is likely to have an increasing impact on city infrastructure. Accurate predictive models of individuals’ movements, their preferences, and their goals are likely to emerge with the greater availability of data. The ethical issues regarding such an emergence are discussed in Section III of this report.

The United States Department of Transportation released a call for proposals in 2016 asking medium-size cities to imagine smart city infrastructure for transportation. This initiative plans to award forty million dollars to a city to demonstrate how technology and data can be used to reimagine the movement of people as well as goods. One vision is a network of connected vehicles that can reach a high level of safety in driving with car-to-car communication. If this vision becomes reality, we expect advances in multi-agent coordination, collaboration, and planning will have a significant impact on future cars and play a role in making the transportation system more reliable and efficient. Robots are also likely to take part in transportation by carrying individuals and packages (c.f., Segway robot). For transportation of goods, interest in drones has increased, and Amazon is currently testing a delivery system using them, although questions remain about the appropriate safety rules and regulations. The increased sensing capabilities, adoption of drones, and the connected transportation infrastructure will also raise concerns about the privacy of individuals and the safety of private data. In coming years, these and related transportation issues will need to be addressed either by preemptive action on the part of industry or within the legal framework. As noted in the Section III policy discussion, how well this is done will affect the pace and scope of AI-related advances in the transportation sector.

On-demand transportation

On-demand transportation services such as Uber and Lyft have emerged as another pivotal application of sensing, connectivity, and AI, with algorithms for matching drivers to passengers by location and suitability (reputation modeling). Through dynamic pricing, these services ration access by willingness-to-pay, with dynamic pricing also encouraging an increase in the supply of drivers, and have become a popular method for transportation in cities. With their rapid advance have come multiple policy and legal issues, such as competition with existing taxi services and concerns about lack of regulation and safety. On-demand transportation services seem likely to be a major force towards self-driving cars.

Carpooling and ridesharing have long been seen as a promising approach to decrease traffic congestion and better utilize personal transportation resources. Services such as Zimride and Nuride bring together people sharing similar routes for a joint trip. But this approach to carpooling has failed to gain traction on a large scale. Interacting with people

For decades, people have imagined wildly different, futuristic-looking transportation vehicles. Although future cars will be smarter and drones will be available widely, it is unlikely that by 2030 we will have widely adopted transportation vehicles that look and function differently than the ones we have today. Our Study Panel doesn’t expect drones that can fly, swim, and drive, or flying quadcoptors to become a common means of transportation in this time horizon (although prototypes exist today). We do expect humans to become partners to self-driving cars and drones in their training, execution, and evaluation. This partnering will happen both when humans are co-located with machines and also virtually. We predict advances in algorithms to facilitate machine learning from human input. We also expect models and algorithms for modeling of human attention, and to support communication and coordination between humans and machine. This is an integral part of the development of future vehicles.

HOME/SERVICE ROBOTS

Robots have entered people’s homes in the past fifteen years. Disappointingly slow growth in the diversity of applications has occurred simultaneously with increasingly sophisticated AI deployed on existing applications. AI advances are often inspired by mechanical innovations, which in turn prompt new AI techniques to be introduced. Over the next fifteen years, coincident advances in mechanical and AI technologies promise to increase the safe and reliable use and utility of home robots in a typical North American city. Special purpose robots will deliver packages, clean offices, and enhance security, but technical constraints and the high costs of reliable mechanical devices will continue to limit commercial opportunities to narrowly defined applications for the foreseeable future. As with self-driving cars and other new transportation machines, the difficulty of creating reliable, market-ready hardware is not to be underestimated.

Vacuum cleaners

In 2001, after many years of development, the Electrolux Trilobite, a vacuum cleaning robot, became the first commercial home robot. It had a simple control system to do obstacle avoidance, and some navigation. A year later, iRobot introduced Roomba, which was a tenth the price of the Trilobite and, with only 512 bytes of RAM, ran a behavior based controller. The most intelligent thing it did was to avoid falling down stairs. Since then, sixteen million Roombas have been deployed all over the world and several other competing brands now exist.

As the processing power and RAM capacity of low cost embedded processors improved from its dismal state in the year 2000, the AI capabilities of these robots also improved dramatically. Simple navigation, self-charging, and actions for dealing with full dust bins were added, followed by ability to deal with electrical cords and rug tassels, enabled by a combination of mechanical improvements and sensor based perception. More recently, the addition of full VSLAM (Visual Simultaneous Location and Mapping)— an AI technology that had been around for twenty years— has enabled the robots to build a complete 3D world model of a house as they clean, and become more efficient in their cleaning coverage.

Early expectations that many new applications would be found for home robots have not materialized. Robot vacuum cleaners are restricted to localized flat areas, while real homes have lots of single steps, and often staircases; there has been very little research on robot mobility inside real homes. Hardware platforms remain challenging to build, and there are few applications that people want enough to buy. Perceptual algorithms for functions such as image labeling, and 3D object recognition, while common at AI conferences, are still only a few years into development as products.

Home robots 2030

Despite the slow growth to date of robots in the home, there are signs that this will change in the next fifteen years. Corporations such as Amazon Robotics and Uber are developing large economies of scale using various aggregation technologies. Also: System in Module (SiM), with a lot of System on Chip (SoC) subsystems, are now being pushed out the door by phone-chip makers (Qualcomm’s SnapDragon, Samsung’s Artik, etc.). These are better than supercomputers of less than ten years ago with eight or more sixty-four-bit cores, and specialized silicon for cryptography, camera drivers, additional DSPs, and hard silicon for certain perceptual algorithms. This means that low cost devices will be able to support much more onboard AI than we have been able to consider over the last fifteen years.

Cloud (“someone else’s computer”) is going to enable more rapid release of new software on home robots, and more sharing of data sets gathered in many different homes, which will in turn feed cloud-based machine learning, and then power improvements to already deployed robots.

The great advances in speech understanding and image labeling enabled by deep learning will enhance robots’ interactions with people in their homes. Low cost 3D sensors, driven by gaming platforms, have fueled work on 3D perception algorithms by thousands of researchers worldwide, which will speed the development and adoption of home and service robots.

In the past three years, low cost and safe robot arms have been introduced to hundreds of research labs around the world, sparking a new class of research on manipulation that will eventually be applicable in the home, perhaps around 2025. More than half a dozen startups around the world are developing AI-based robots for the home, for now concentrating mainly on social interaction. New ethics and privacy issues may surface as a result.

HEALTHCARE

For AI technologies, healthcare has long been viewed as a promising domain. AI-based applications could improve health outcomes and quality of life for millions of people in the coming years—but only if they gain the trust of doctors, nurses, and patients, and if policy, regulatory, and commercial obstacles are removed. Prime applications include clinical decision support, patient monitoring and coaching, automated devices to assist in surgery or patient care, and management of healthcare systems. Recent successes, such as mining social media to infer possible health risks, machine learning to predict patients at risk, and robotics to support surgery, have expanded a sense of possibility for AI in healthcare. Improvements in methods for interacting with medical professionals and patients will be a critical challenge.

As in other domains, data is a key enabler. There has been an immense forward leap in collecting useful data from personal monitoring devices and mobile apps, from electronic health records (EHR) in clinical settings and, to a lesser extent, from robots designed to assist with medical procedures and hospital operations. But using this data to enable more finely-grained diagnostics and treatments for both individual patients and patient populations has proved difficult. Research and deployment have been slowed by outdated regulations and incentive structures. Poor human-computer interaction methods and the inherent difficulties and risks of implementing technologies in such a large and complex system have slowed realization of AI’s promise in healthcare.The reduction or removal of these obstacles, combined with innovations still on the horizon, have the potential to significantly improve health outcomes and quality of life for millions of people in the coming years. The clinical setting

For decades, the vision of an AI-powered clinician’s assistant has been a near cliché. Although there have been successful pilots of AI-related technology in healthcare, the current healthcare delivery system unfortunately remains structurally ill-suited to absorb and deploy rapid advances. Incentives provided by the Affordable Care Act have accelerated the penetration of electronic health records (EHRs) into clinical practice, but implementation has been poor, eroding clinicians’ confidence in their usefulness. A small group of companies control the EHR market, and user interfaces are widely considered substandard, including annoying pop-ups that physicians routinely dismiss. The promise of new analytics using data from EHRs, including AI, remains largely unrealized due to these and other regulatory and structural barriers.

Looking ahead to the next fifteen years, AI advances, if coupled with sufficient data and well-targeted systems, promise to change the cognitive tasks assigned to human clinicians. Physicians now routinely solicit verbal descriptions of symptoms from presenting patients and, in their heads, correlate patterns against the clinical presentation of known diseases. With automated assistance, the physician could instead supervise this process, applying her or his experience and intuition to guide the input process and to evaluate the output of the machine intelligence. The literal “hands-on” experience of the physician will remain critical. A significant challenge is to optimally integrate the human dimensions of care with automated reasoning processes.

To achieve future advances, clinicians must be involved and engaged at the outset to ensure that systems are well-engineered and trusted. Already, a new generation of more tech savvy physicians routinely utilize specialized apps on mobile devices. At the same time, workloads on primary care clinicians have increased to the point that they are grateful for help from any quarter. Thus, the opportunity to exploit new learning methods, to create structured patterns of inference by mining the scientific literature automatically, and to create true cognitive assistants by supporting free-form dialogue, has never been greater. Provided these advances are not stymied by regulatory, legal, and social barriers, immense improvements to the value of healthcare are within our grasp.

Healthcare analytics

At the population level, AI’s ability to mine outcomes from millions of patient clinical records promises to enable finer-grained, more personalized diagnosis and treatment. Automated discovery of genotype-phenotype connections will also become possible as full, once-in-a-lifetime genome sequencing becomes routine for each patient. A related (and perhaps earlier) capability will be to find “patients like mine” as a way to inform treatment decisions based on analysis of a similar cohort. Traditional and non-traditional healthcare data, augmented by social platforms, may lead to the emergence of self-defined subpopulations, each managed by a surrounding ecosystem of healthcare providers augmented with automated recommendation and monitoring systems.

These developments have the potential to radically transform healthcare delivery as medical procedures and lifetime clinical records for hundreds of millions of individuals become available. Similarly, the automated capture of personal environmental data from wearable devices will expand personalized medicine. These activities are becoming more commercially viable as vendors discover ways to engage large populations (e.g. ShareCare) and then to create population-scale data that can be mined to produce individualized analytics and recommendations.

Unfortunately, the FDA has been slow to approve innovative diagnostic software, and there are many remaining barriers to rapid innovation. HIPAA (Health Insurance Portability and Accountability Act) requirements for protecting patient privacy create legal barriers to the flow of patient data to applications that could utilize AI technologies.

Unanticipated negative effects of approved drugs could show up routinely, sooner, and more rigorously than they do today, but mobile apps that analyze drug interactions may be blocked from pulling the necessary information from patient records. More generally, AI research and innovation in healthcare are hampered by the lack of widely accepted methods and standards for privacy protection. The FDA has been slow to approve innovative software, in part due to an unclear understanding of the cost/benefit tradeoffs of these systems. If regulators (principally the FDA) recognize that effective post-marketing reporting is a dependable hedge against some safety risks, faster initial approval of new treatments and interventions may become possible.

Automated image interpretation has also been a promising subject of study for decades. Progress on interpreting large archives of weakly-labeled images, such as large photo archives scraped from the web, has been explosive. At first blush, it is surprising that there has not been a similar revolution in interpretation of medical images. Most medical imaging modalities (CT, MR, ultrasound) are inherently digital, the images are all archived, and there are large, established companies with internal R&D (e.g. Siemens, Philips, GE) devoted to imaging.

But several barriers have limited progress to date. Most hospital image archives have only gone digital over the past decade. More importantly, the problem in medicine is not to recognize what is in the image (is this a liver or a kidney?), but rather to make a fine-grained judgement about it (does the slightly darker smudge in the liver suggest a potentially cancerous tumor?). Strict regulations govern these high-stakes judgements. Even with state-of-the-art technologies, a radiologist will still likely have to look at the images, so the value proposition is not yet compelling. Also, healthcare regulations preclude easy federation of data across institutions. Thus, only very large organizations of integrated care, such as Kaiser Permanente, are able to attack these problems.

Still, automated/augmented image interpretation has started to gain momentum. The next fifteen years will probably not bring fully automated radiology, but initial forays into image “triage” or second level checking will likely improve the speed and costeffectiveness of medical imaging. When coupled with electronic patient record systems, large-scale machine learning techniques could be applied to medical image data. For example, multiple major healthcare systems have archives of millions of patient scans, each of which has an associated radiological report, and most have an associated patient record. Already, papers are appearing in the literature showing that deep neural networks can be trained to produce basic radiological findings, with high reliability, by training from this data.

Healthcare robotics

Fifteen years ago, healthcare robotics was largely science fiction. One company called Robodoc, a spin-out from IBM, developed robotic systems for orthopedic surgeries, such as hip and knee replacements. The technology worked, but the company struggled commercially, and was ultimately shut down and acquired for its technology. More recently, though, the research and practical use of surgical robotics has exploded.

In 2000 Intuitive Surgical introduced the da Vinci system, a novel technology initially marketed to support minimally invasive heart bypass surgery, and then gained substantial market traction for treatment of prostate cancer and merged with its only major competition, Computer Motion, in 2003. The da Vinci, now in its fourth generation, provides 3D visualization (as opposed to 2D monocular laparoscopy) and wristed instruments in an ergonomic platform. It is considered the standard of care in multiple laparoscopic procedures, and used in nearly three quarters of a million procedures a year, providing not only a physical platform, but also a new data platform for studying the process of surgery.

The da Vinci anticipates a day when much greater insight into how medical professionals carry out the process of providing interventional medical care will be possible. The presence of the da Vinci in day-to-day operation has also opened the doors to new types of innovation—from new instrumentation to image fusion to novel biomarkers—creating its own innovation ecosystem. The success of the platform has inspired potential competitors in robotic surgery, most notably the Alphabet spin-off Verb, in collaboration with J&J/Ethicon. There are likely to be many more, each exploring a unique niche or space and building out an ecosystem of sensing, data analytics, augmentation, and automation.

Intelligent automation in hospital operations has been less successful. The story is not unlike surgical robotics. Twenty years ago, one company, HelpMate, created a robot for hospital deliveries, such as meals and medical records, but ultimately went bankrupt. More recently, Aethon introduced TUG Robots for basic deliveries, but few hospitals have invested in this technology to date. However, robotics in other service industries such as hotels and warehouses, including Amazon Robotics (formerly Kiva), are demonstrating that these technologies are practical and cost effective in at least some large-scale settings, and may ultimately spur additional innovation in health care.

Looking ahead, many tasks that appear in healthcare will be amenable to augmentation, but will not be fully automated. For example, robots may be able to deliver goods to the right room in a hospital, but then require a person to pick them up and place them in their final location. Walking a patient down the corridor may be relatively simple once a patient is standing in a walker (though will certainly not be trivial for patients recovering from surgery and/or elderly patients, especially in corridors crowded with equipment and other people). Driving a needle to place a suture is relatively straightforward once the needle is correctly placed. This implies that many future systems will involve intimate interaction between people and machines and require technologies that facilitate collaboration between them. The growth of automation will enable new insights into healthcare processes.

Historically, robotics has not been a strongly data-driven or data-oriented science. This is changing as (semi)automation infiltrates healthcare. As the new surgical, delivery, and patient care platforms come online, the beginnings of quantification and predictive analytics are being built on top of data coming from these platforms. This data will be used to assess quality of performance, identify deficiencies, errors, or potential optimizations, and will be used as feedback to improve performance. In short, these platforms will facilitate making the connection between what is done, and the outcome achieved, making true “closed-loop” medicine a real possibility. Mobile health

To date, evidence-driven analytics on healthcare have relied on traditional healthcare data—mainly the electronic medical records discussed above. In the clinical setting, there are hopeful trends towards bringing new data to bear. For example, TeleLanguage enables a human clinician to conduct language therapy sessions with multiple patients simultaneously with the aid of an AI agent trained by the clinician. And Lifegraph, which extracts behavioral patterns and creates alerts from data passively collected from a patient’s smartphone, has been adopted by psychiatrists in Israel to detect early signs of distressful behavior in patients.

Looking ahead, driven by the mobile computing revolution, the astonishing growth of “biometrics in the wild”—and the explosion of platforms and applications that use them—is a hopeful and unanticipated trend. Thousands of mobile apps now offer information, introduce behavior modification, or identify groups of “people like me.” This, combined with the emerging trend of more specialized motion tracking devices, such as Fitbit, and the emerging (inter)connectedness between the home environment and health-monitoring devices, has created a vibrant new sector of innovation. By combining social and healthcare data, some healthcare apps can perform data mining, learning, and prediction from captured data, though their predictions are relatively rudimentary. The convergence of data and functionality across applications will likely spur new and even obvious products, such as an exercise app that not only proposes a schedule for exercise but also suggests the best time to do it, and provides coaching to stick to that schedule.

Elder care

Over the next fifteen years the number of elderly in the United States will grow by over 50%. The National Bureau of Labor Statistics projects that home health aides will grow 38% over the next ten years. Despite the broad opportunities in this domain—basic social support, interaction and communication devices, home health monitoring, a variety of simple in-home physical aids such as walkers, and light meal preparation—little has happened over the past fifteen years. But the coming generational shift will accompany a change in technology acceptance among the elderly. Currently, someone who is seventy was born in 1946 and may have first experienced some form of personalized IT in middle age or later, while a fifty-year-old today is far more technology-friendly and savvy. As a result, there will be a growing interest and market for already available and maturing technologies to support physical, emotional, social, and mental health. Here are a few likely examples by category: Life quality and independence

- Automated transportation will support continued independence and expanded social horizons.

- Sharing of information will help families remain engaged with one another at a distance, and predictive analytics may be used to “nudge” family groups toward positive behaviors, such as reminders to “call home.”

- Smart devices in the home will help with daily living activities when needed, such as cooking and, if robot manipulation capabilities improve sufficiently, dressing and toileting. Health and wellness

- Mobile applications that monitor movement and activities, coupled with social platforms, will be able to make recommendations to maintain mental and physical health.

- In-home health monitoring and health information access will be able to detect changes in mood or behavior and alert caregivers.

- Personalized health management will help mitigate the complexities associated with multiple co-morbid conditions and/or treatment interactions. Treatments and devices

- Better hearing aids and visual assistive devices will mitigate the effects of hearing and vision loss, improving safety and social connection.

- Personalized rehabilitation and in-home therapy will reduce the need for hospital or care facility stays.

- Physical assistive devices (intelligent walkers, wheel chairs, and exoskeletons) will extend the range of activities of an infirm individual.

The Study Panel expects an explosion of low-cost sensing technologies that can provide substantial capabilities to the elderly in their homes. In principle, social agents with a physical presence and simple physical capabilities (e.g. a mobile robot with basic communication capabilities) could provide a platform for new innovations. However, doing so will require integration across multiple areas of AI—Natural Language Processing, reasoning, learning, perception, and robotics—to create a system that is useful and usable by the elderly. These innovations will also introduce questions regarding privacy within various circles, including friends, family, and care-givers, and create new challenges to accommodate an evermore active and engaged population far past retirement.

EDUCATION

The past fifteen years have seen considerable AI advances in education. Applications are in wide use by educators and learners today, with some variation between K-12 and university settings. Though quality education will always require active engagement by human teachers, AI promises to enhance education at all levels, especially by providing personalization at scale. Similar to healthcare, resolving how to best integrate human interaction and face-to-face learning with promising AI technologies remains a key challenge.

Robots have long been popular educational devices, starting with the early Lego Mindstorms kits developed with the MIT Media Lab in the 1980s. Intelligent Tutoring Systems (ITS) for science, math, language, and other disciplines match students with interactive machine tutors. Natural Language Processing, especially when combined with machine learning and crowdsourcing, has boosted online learning and enabled teachers to multiply the size of their classrooms while simultaneously addressing individual students’ learning needs and styles. The data sets from large online learning systems have fueled rapid growth in learning analytics. Still, schools and universities have been slow in adopting AI technologies primarily due to lack of funds and lack of solid evidence that they help students achieve learning objectives. Over the next fifteen years in a typical North American city, the use of intelligent tutors and other AI technologies to assist teachers in the classroom and in the home is likely to expand significantly, as will learning based on virtual reality applications. But computer-based learning systems are not likely to fully replace human teaching in schools.

Teaching robots

Today, more sophisticated and versatile kits for use in K-12 schools are available from a number of companies that create robots with new sensing technologies programmable in a variety of languages. Ozobot is a robot that teaches children to code and reason deductively while configuring it to dance or play based on color-coded patterns. Cubelets help teach children logical thinking through assembling robot blocks to think, act, or sense, depending upon the function of the different blocks. Wonder Workshop’s Dash and Dot span a range of programming capabilities. Children eight years old and older can create simple actions using a visual programming language, Blockly, or build iOS and Android applications using C or Java. PLEO rb is a robot pet that helps children learn biology by teaching the robot to react to different aspects of the environment. However, while fun and engaging for some, in order for such kits to become widespread, there will need to be compelling evidence that they improve students’ academic performance. Intelligent Tutoring Systems (ITS) and online learning

ITS have been developed from research laboratory projects such as Why-2 Atlas, which supported human-machine dialogue to solve physics problems early in the era. The rapid migration of ITS from laboratory experimental stages to real use is surprising and welcome. Downloadable software and online systems such as Carnegie Speech or Duolingo provide foreign language training using Automatic Speech Recognition (ASR) and NLP techniques to recognize language errors and help users correct them. Tutoring systems such as the Carnegie Cognitive Tutor have been used in US high schools to help students learn mathematics. Other ITS have been developed for training in geography, circuits, medical diagnosis, computer literacy and programming, genetics, and chemistry. Cognitive tutors use software to mimic the role of a good human tutor by, for example, providing hints when a student gets stuck on a math problem. Based on the hint requested and the answer provided, the tutor offers context specific feedback.

Applications are growing in higher education. An ITS called SHERLOCK is beginning to be used to teach Air Force technicians to diagnose electrical systems problems in aircraft. And the University of Southern California’s Information Sciences Institute has developed more advanced avatar-based training modules to train military personnel being sent to international posts in appropriate behavior when dealing with people from different cultural backgrounds. New algorithms for personalized tutoring, such as Bayesian Knowledge Tracing, enable individualized mastery learning and problem sequencing.

Most surprising has been the explosion of the Massive Open Online Courses (MOOCs) and other models of online education at all levels—including the use of tools like Wikipedia and Khan Academy as well as sophisticated learning management systems that build in synchronous as well as asynchronous education and adaptive learning tools. Since the late 1990s, companies such as the Educational Testing Service and Pearson have been developing automatic NLP assessment tools to co-grade essays in standardized testing. Many of the MOOCs which have become so popular, including those created by EdX, Coursera, and Udacity, are making use of NLP, machine learning, and crowdsourcing techniques for grading short-answer and essay questions as well as programming assignments. Online education systems that support graduate-level professional education and lifelong learning are also expanding rapidly. These systems have great promise because the need for face-to-face interaction is less important for working professionals and career changers. While not the leaders in AI-supported systems and applications, they will become early adopters as the technologies are tested and validated.

It can be argued that AI is the secret sauce that has enabled instructors, particularly in higher education, to multiply the size of their classrooms by a few orders of magnitude—class sizes of a few tens of thousands are not uncommon. In order to continually test large classes of students, automated generation of the questions is also possible, such as those designed to assess vocabulary, wh (who/what/when/ where/why) questions, and multiple choice questions, using electronic resources such as WordNet, Wikipedia, and online ontologies. With the explosion of online courses, these techniques are sure to be eagerly adopted for use in online education. Although the long term impact of these systems will have on the educational system remains unclear, the AI community has learned a great deal in a very short time. Learning analytics

Data sets being collected from massive scale online learning systems, ranging from MOOCs to Khan Academy, as well as smaller scale online programs, have fueled the rapid growth of the field of learning analytics. Online courses are not only good for widespread delivery, but are natural vehicles for data collection and experimental instrumentation that will contribute to scientific findings and improving the quality of learning at scale. Organizations such as the Society for Learning Analytics Research (SOLAR), and the rise of conferences including the Learning Analytics and Knowledge Conference and the Learning at Scale Conference (L@S) reflect this trend. This community applies deep learning, natural language processing, and other AI techniques to analysis of student engagement, behavior, and outcomes.

Current projects seek to model common student misconceptions, predict which students are at risk of failure, and provide real-time student feedback that is tightly integrated with learning outcomes. Recent work has also been devoted to understanding the cognitive processes involved in comprehension, writing, knowledge acquisition, and memory, and to applying that understanding to educational practice by developing and testing educational technologies.

Challenges and opportunities

One might have expected more and more sophisticated use of AI technologies in schools, colleges, and universities by now. Much of its absence can be explained by the lack of financial resources of these institutions as well as the lack of data establishing the technologies’ effectiveness. These problems are being addressed, albeit slowly, by private foundations and by numerous programs to train primarily secondary school teachers in summer programs. As in other areas of AI, excessive hype and promises about the capabilities of MOOCs have meant that expectations frequently exceed the reality. The experiences of certain institutions, such as San Jose State University’s experiment with Udacity, have led to more sober assessment of the potential of the new educational technologies

In the next fifteen years, it is likely that human teachers will be assisted by AI technologies with better human interaction, both in the classroom and in the home. The Study Panel expects that more general and more sophisticated virtual reality scenarios in which students can immerse themselves in subjects from all disciplines will be developed. Some steps in this direction are being taken now by increasing collaborations between AI researchers and researchers in the humanities and social sciences, exemplified by Stanford’s Galileo Correspondence Project and Columbia’s Making and Knowing Project. These interdisciplinary efforts create interactive experiences with historical documents and the use of Virtual Reality (VR) to explore interactive archeological sites. VR techniques are already being used in the natural sciences such as biology, anatomy, geology and astronomy to allow students to interact with environments and objects that are difficult to engage with in the real world. The recreation of past worlds and fictional worlds will become just as popular for studies of arts and other sciences.

AI techniques will increasingly blur the line between formal, classroom education and self-paced, individual learning. Adaptive learning systems, for example, are going to become a core part of the teaching process in higher education because of the pressures to contain cost while serving a larger number of students and moving students through school more quickly. While formal education will not disappear, the Study Panel believes that MOOCs and other forms of online education will become part of learning at all levels, from K-12 through university, in a blended classroom experience. This development will facilitate more customizable approaches to learning, in which students can learn at their own pace using educational techniques that work best for them. Online education systems will learn as the students learn, supporting rapid advances in our understanding of the learning process. Learning analytics, in turn, will accelerate the development of tools for personalized education.

The current transition from hard copy books to digital and audio media and texts is likely to become prevalent in education as well. Digital reading devices will also become much ‘smarter’, providing students with easy access to additional information about subject matter as they study. Machine Translation (MT) technology will also make it easier to translate educational material into different languages with a fair degree of accuracy, just as it currently translates technical manuals. Textbook translation services that currently depend only upon human translators will increasingly incorporate automatic methods to improve the speed and affordability of their services for school systems.

Online learning systems will also expand the opportunity for adults and working professionals to enhance their knowledge and skills (or to retool and learn a new field) in a world where these fields are evolving rapidly. This will include the expansion of fully online professional degrees as well as professional certifications based on online coursework.

Broader societal consequences

In countries where education is difficult for the broad population to obtain, online resources may have a positive effect if the population has the tools to access them. The development of online educational resources should make it easier for foundations that support international educational programs to provide quality education by providing tools and relatively simple amounts of training in their use. For example, large numbers of educational apps, many of them free, are being developed for the iPad. On the negative side, there is already a major trend among students to restrict their social contacts to electronic ones and to spend large amounts of time without social contact, interacting with online programs. If education also occurs more and more online, what effect will the lack of regular, face-to-face contact with peers have on students’ social development? Certain technologies have even been shown to create neurological side effects. On the other hand, autistic children have benefited from interactions with AI systems already.

LOW-RESOURCE COMMUNITIES

Many opportunities exist for AI to improve conditions for people in low-resource communities in a typical North American city—and, indeed, in some cases it already has. Understanding these direct AI contributions may also inform potential contributions in the poorest parts of the developing world. There has not been a significant focus on these populations in AI gatherings, and, traditionally, AI funders have underinvested in research lacking commercial application. With targeted incentives and funding priorities, AI technologies could help address the needs of low-resource communities. Budding efforts are promising. Counteracting fears that AI may contribute to joblessness and other societal problems, AI may provide mitigations and solutions, particularly if implemented in ways that build trust in them by the affected communities. Machine learning, data mining approaches

Under the banner of “data science for social good,” AI has been used to create predictive models to help government agencies more effectively use their limited budgets to address problems such as lead poisoning, a major public health concern that has been in the news due to ongoing events in Flint, Michigan. Children may be tested for elevated lead levels, but that unfortunately means the problem is only detected after they have already been poisoned. Many efforts are underway to use predictive models to assist government agencies in prioritizing children at risk, including those who may not yet have been exposed. Similarly, the Illinois Department of Human Services (IDHS) uses predictive models to identify pregnant women at risk for adverse birth outcomes in order to maximize the impact of prenatal care. The City of Cincinnati uses them to proactively identify and deploy inspectors to properties at risk of code violations.

Scheduling, planning

Task assignment scheduling and planning techniques have been applied by many different groups to distribute food before it spoils from those who may have excess, such as restaurants, to food banks, community centers and individuals. Reasoning with social networks and influence maximization

Social networks can be harnessed to create earlier, less-costly interventions involving large populations. For example, AI might be able to assist in spreading healthrelated information. In Los Angeles, there are more than 5,000 homeless youth (ages thirteen-twenty-four). Individual interventions are difficult and expensive, and the youths’ mistrust of authority dictates that key messages are best spread through peer leaders. AI programs might be able to leverage homeless youth social networks to strategically select peer leaders to spread health-related information, such as how to avoid spread of HIV. The dynamic, uncertain nature of these networks does pose challenges for AI research. Care must also be taken to prevent AI systems from reproducing discriminatory behavior, such as machine learning that identifies people through illegal racial indicators, or through highly-correlated surrogate factors, such as zip codes. But if deployed with great care, greater reliance on AI may well result in a reduction in discrimination overall, since AI programs are inherently more easily audited than humans.

PUBLIC SAFETY AND SECURITY

Cities already have begun to deploy AI technologies for public safety and security. By 2030, the typical North American city will rely heavily upon them. These include cameras for surveillance that can detect anomalies pointing to a possible crime, drones, and predictive policing applications. As with most issues, there are benefits and risks. Gaining public trust is crucial. While there are legitimate concerns that policing that incorporates AI may become overbearing or pervasive in some contexts, the opposite is also possible. AI may enable policing to become more targeted and used only when needed. And assuming careful deployment, AI may also help remove some of the bias inherent in human decision-making.

One of the more successful uses of AI analytics is in detecting white collar crime, such as credit card fraud. Cybersecurity (including spam) is a widely shared concern, and machine learning is making an impact. AI tools may also prove useful in helping police manage crime scenes or search and rescue events by helping commanders prioritize tasks and allocate resources, though these tools are not yet ready for automating such activities. Improvements in machine learning in general, and transfer learning in particular—for speeding up learning in new scenarios based on similarities with past scenarios—may facilitate such systems.

The cameras deployed almost everywhere in the world today tend to be more useful for helping solve crimes than preventing them. This is due to the low quality of event identification from videos and the lack of manpower to look at massive video streams. As AI for this domain improves, it will better assist crime prevention and prosecution through greater accuracy of event classification and efficient automatic processing of video to detect anomalies—including, potentially, evidence of police malpractice. These improvements could lead to even more widespread surveillance. Some cities have already added drones for surveillance purposes, and police use of drones to maintain security of ports, airports, coastal areas, waterways, industrial facilities is likely to increase, raising concerns about privacy, safety, and other issues.

The New York Police Department’s CompStat was the first tool pointing toward predictive policing, and many police departments now use it. Machine learning significantly enhances the ability to predict where and when crimes are more likely to happen and who may commit them. As dramatized in the movie Minority Report, predictive policing tools raise the specter of innocent people being unjustifiably targeted. But well-deployed AI prediction tools have the potential to actually remove or reduce human bias, rather than reinforcing it, and research and resources should be directed toward ensuring this effect.

AI techniques can be used to develop intelligent simulations for training lawenforcement personnel to collaborate. While international criminal organizations and terrorists from different countries are colluding, police forces from different countries still face difficulty in joining forces to fight them. Training international groups of law enforcement personnel to work as teams is very challenging. The European Union, through the Horizon 2020 program, currently supports such attempts in projects such as LawTrain. The next step will be to move from simulation to actual investigations by providing tools that support such collaborations.

Tools do exist for scanning Twitter and other feeds to look for certain types of events and how they may impact security. For example, AI can help in social network analysis to prevent those at risk from being radicalized by ISIS or other violent groups. Law enforcement agencies are increasingly interested in trying to detect plans for disruptive events from social media, and also to monitor activity at large gatherings of people to analyze security. There is significant work on crowd simulations to determine how crowds can be controlled. At the same time, legitimate concerns have been raised about the potential for law enforcement agencies to overreach and use such tools to violate people’s privacy.

The US Transportation Security Administration (TSA), Coast Guard, and the many other security agencies that currently rely on AI will likely increase their reliance to enable significant efficiency and efficacy improvements. AI techniques— vision, speech analysis, and gait analysis— can aid interviewers, interrogators, and security guards in detecting possible deception and criminal behavior. For example, the TSA currently has an ambitious project to redo airport security nationwide. Called DARMS, the system is designed to improve efficiency and efficacy of airport security by relying on personal information to tailor security based on a person’s risk categorization and the flights being taken. The future vision for this project is a tunnel that checks people’s security while they walk through it. Once again, developers of this technology should be careful to avoid building in bias (e.g. about a person’s risk level category) through use of datasets that reflect prior bias.

EMPLOYMENT AND WORKPLACE

While AI technologies are likely to have a profound future impact on employment and workplace trends in a typical North American city, it is difficult to accurately assess current impacts, positive or negative. In the past fifteen years, employment has shifted due to a major recession and increasing globalization, particularly with China’s introduction to the world economy, as well as enormous changes in non-AI digital technology. Since the 1990s, the US has experienced continued growth in productivity and GDP, but median income has stagnated and the employment to population ratio has fallen.

There are clear examples of industries in which digital technologies have had profound impacts, good and bad, and other sectors in which automation will likely make major changes in the near future. Many of these changes have been driven strongly by “routine” digital technologies, including enterprise resource planning, networking, information processing, and search. Understanding these changes should provide insights into how AI will affect future labor demand, including the shift in skill demands. To date, digital technologies have been affecting workers more in the skilled middle, such as travel agents, rather than the very lowest-skilled or highest skilled work. On the other hand, the spectrum of tasks that digital systems can do is evolving as AI systems improve, which is likely to gradually increase the scope of what is considered routine. AI is also creeping into high end of the spectrum, including professional services not historically performed by machines.

To be successful, AI innovations will need to overcome understandable human fears of being marginalized. AI will likely replace tasks rather than jobs in the near term, and will also create new kinds of jobs. But the new jobs that will emerge are harder to imagine in advance than the existing jobs that will likely be lost. Changes in employment usually happen gradually, often without a sharp transition, a trend likely to continue as AI slowly moves into the workplace. A spectrum of effects will emerge, ranging from small amounts of replacement or augmentation to complete replacement. For example, although most of a lawyer’s job is not yet automated, AI applied to legal information extraction and topic modeling has automated parts of first-year lawyers’ jobs. In the not too distant future, a diverse array of job-holders, from radiologists to truck drivers to gardeners, may be affected.

AI may also influence the size and location of the workforce. Many organizations and institutions are large because they perform functions that can be scaled only by adding human labor, either “horizontally” across geographical areas or “vertically” in management hierarchies. As AI takes over many functions, scalability no longer implies large organizations. Many have noted the small number of employees of some high profile internet companies, but not of others. There may be a natural scale of human enterprise, perhaps where the CEO can know everyone in the company. Through the creation of efficiently outsourced labor markets enabled by AI, enterprises may tend towards that natural size.

AI will also create jobs, especially in some sectors, by making certain tasks more important, and create new categories of employment by making new modes of interaction possible. Sophisticated information systems can be used to create new markets, which often have the effect of lowering barriers to entry and increasing participation—from app stores to AirBnB to taskrabbit. A vibrant research community within AI studies further ways of creating new markets and making existing ones operate more efficiently.

While work has intrinsic value, most people work to be able to purchase goods and services they value. Because AI systems perform work that previously required human labor, they have the effect of lowering the cost of many goods and services, effectively making everyone richer. But as exemplified in current political debates, job loss is more salient to people—especially those directly affected—than diffuse economic gains, and AI unfortunately is often framed as a threat to jobs rather than a boon to living standards.

There is even fear in some quarters that advances in AI will be so rapid as to replace all human jobs—including those that are largely cognitive or involve judgment—within a single generation. This sudden scenario is highly unlikely, but AI will gradually invade almost all employment sectors, requiring a shift away from human labor that computers are able to take over.

The economic effects of AI on cognitive human jobs will be analogous to the effects of automation and robotics on humans in manufacturing jobs. Many middle-aged workers have lost well-paying factory jobs and the socio-economic status in family and society that traditionally went with such jobs. An even larger fraction of the total workforce may, in the long run, lose well-paying “cognitive” jobs. As labor becomes a less important factor in production as compared to owning intellectual capital, a majority of citizens may find the value of their labor insufficient to pay for a socially acceptable standard of living. These changes will require a political, rather than a purely economic, response concerning what kind of social safety nets should be in place to protect people from large, structural shifts in the economy. Absent mitigating policies, the beneficiaries of these shifts may be a small group at the upper stratum of the society.

In the short run, education, re-training, and inventing new goods and services may mitigate these effects. Longer term, the current social safety net may need to evolve into better social services for everyone, such as healthcare and education, or a guaranteed basic income. Indeed, countries such as Switzerland and Finland have actively considered such measures. AI may be thought of as a radically different mechanism of wealth creation in which everyone should be entitled to a portion of the world’s AI-produced treasure. It is not too soon for social debate on how the economic fruits of AI-technologies should be shared. As children in traditional societies support their aging parents, perhaps our artificially intelligent “children” should support us, the “parents” of their intelligence.

ENTERTAINMENT

With the explosive growth of the internet over the past fifteen years, few can imagine their daily lives without it. Powered by AI, the internet has established user-generated content as a viable source of information and entertainment. Social networks such as Facebook are now pervasive, and they function as personalized channels of social interaction and entertainment—sometimes to the detriment of interpersonal interaction. Apps such as WhatsApp and Snapchat enable smart-phone users to remain constantly “in touch” with peers and share sources of entertainment and information. In on-line communities such as Second Life and role-playing games such as World of Warcraft, people imagine an alternative existence in a virtual world. Specialized devices, such as Amazon’s Kindle have also redefined the essentials of long-cherished pastimes. Books can now be browsed and procured with a few swipes of the finger, stored by the thousands in a pocket-sized device, and read in much the same way as a handheld paperback.

Trusted platforms now exist for sharing and browsing blogs, videos, photos, and topical discussions, in addition to a variety of other user-generated information. To operate at the scale of the internet, these platforms must rely on techniques that are being actively developed in natural language processing, information retrieval, image processing, crowdsourcing, and machine learning. Algorithms such as collaborative filtering have been developed, for example, to recommend relevant movies, songs, or articles based on the user’s demographic details and browsing history.

Traditional sources of entertainment have also embraced AI to keep pace with the times. As exemplified in the book and movie Moneyball, professional sport is now subjected to intensive quantitative analysis. Beyond aggregate performance statistics, on-field signals can be monitored using sophisticated sensors and cameras. Software has been created for composing music and recognizing soundtracks. Techniques from computer vision and NLP have been used in creating stage performances. Even the lay user can exercise his or her creativity on platforms such as WordsEye, which automatically generates 3D scenes from natural language text. AI has also come to the aid of historical research in the arts, and is used extensively in stylometry and, more recently, in the analysis of paintings.

The enthusiasm with which humans have responded to AI-driven entertainment has been surprising and led to concerns that it reduces interpersonal interaction among human beings. Few predicted that people would spend hours on end interacting with a display. Children often appear to be genuinely happier playing at home on their devices rather than outside with their friends. AI will increasingly enable entertainment that is more interactive, personalized, and engaging. Research should be directed toward understanding how to leverage these attributes for individuals’ and society’s benefit.

Imagining the Future

The success of any form of entertainment is ultimately determined by the individuals and social groups that are its subjects. The modes of entertainment that people find appealing are diverse and change over time. It is therefore hard to predict the forms entertainment will take in the next fifteen years precisely. Nevertheless, current trends suggest at least a few features that the future entertainment landscape is likely to contain. To date, the information revolution has mostly unfolded in software. However, with the growing availability of cheaper sensors and devices, greater innovation in the hardware used in entertainment systems is expected. Virtual reality and haptics could enter our living rooms—personalized companion robots are already being developed.

With the accompanying improvements in Automatic Speech Recognition, the Study Panel expects that interaction with robots and other entertainment systems will become dialogue-based, perhaps constrained at the start, but progressively more human-like. Equally, the interacting systems are predicted to develop new characteristics such as emotion, empathy, and adaptation to environmental rhythms such as time of day. Today, an amateur with a video camera and readily-available software tools can make a relatively good movie. In the future, more sophisticated tools and apps will become available to make it even easier to produce high-quality content, for example, to compose music or to choreograph dance using an avatar. The creation and dissemination of entertainment will benefit from the progress of technologies such as ASR, dubbing, and Machine Translation, which will enable content to be customized to different audiences inexpensively. This democratization and proliferation of AIcreated media makes it difficult to predict how humans’ taste for entertainment, which are already fluid, will evolve.

With content increasingly delivered digitally, and large amounts of data being logged about consumers’ preferences and usage characteristics, media powerhouses will be able to micro-analyze and micro-serve content to increasingly specialized segments of the population—down to the individual. Conceivably the stage is set for the emergence of media conglomerates acting as “Big Brothers” who are able to control the ideas and online experiences to which specific individuals are exposed. It remains to be seen whether broader society will develop measures to prevent their emergence. This topic, along with others pertaining to AI-related policy, is treated in more detail in the next section

SECTION III: PROSPECTS AND RECOMMENDATIONS FOR AI PUBLIC POLICY

The goal of AI applications must be to create value for society. Our policy recommendations flow from this goal, and, while this report is focused on a typical North American city in 2030, the recommendations are broadly applicable to other places over time. Strategies that enhance our ability to interpret AI systems and participate in their use may help build trust and prevent drastic failures. Care must be taken to augment and enhance human capabilities and interaction, and to avoid discrimination against segments of society. Research to encourage this direction and inform public policy debates should be emphasized. Given the current sector-specific regulation of US industries, new or retooled laws and policies will be needed to address the widespread impacts AI is likely to bring. Rather than “more” or “stricter” regulation, policies should be designed to encourage helpful innovation, generate and transfer expertise, and foster broad corporate and civic responsibility for addressing critical societal issues raised by these technologies. In the long term, AI will enable new wealth creation that will require social debate on how the economic fruits of AI technologies should be shared.

AI POLICY, NOW AND IN THE FUTURE

Throughout history, humans have both shaped and adapted to new technologies. This report anticipates that advances in AI technologies will be developed and fielded gradually—not in sudden, unexpected jumps in the techniques themselves—and will build on what exists today, making this adaptation easier. On the other hand, small improvements to techniques, computing power, or availability of data can occasionally lead to novel, game-changing applications. The measure of success for AI applications is the value they create for human lives. Going forward, the ease with which people use and adapt to AI applications will likewise largely determine their success.

Conversely, since AI applications are susceptible to errors and failures, a mark of their success will be how users perceive and tolerate their shortcomings. As AI becomes increasingly embedded in daily lives and used for more critical tasks, system mistakes may lead to backlash from users and negatively affect their trust. Though accidents in a self-driving car may be less probable than those driven by humans, for example, they will attract more attention. Design strategies that enhance the ability of humans to understand AI systems and decisions (such as explicitly explaining those decisions), and to participate in their use, may help build trust and prevent drastic failures. Likewise, developers should help manage people’s expectations, which will affect their happiness and satisfaction with AI applications. Frustration in carrying out functions promised by a system diminishes people’s trust and reduces their willingness to use the system in the future.

Another important consideration is how AI systems that take over certain tasks will affect people’s affordances and capabilities. As machines deliver super-human performances on some tasks, people’s ability to perform them may wither. Already, introducing calculators to classrooms has reduced children’s ability to do basic arithmetic operations. Still, humans and AI systems have complementary abilities. People are likely to focus on tasks that machines cannot do as well, including complex reasoning and creative expression.

Already, children are increasingly exposed to AI applications, such as interacting with personal assistants on cell phones or with virtual agents in theme parks. Having early exposure will improve children’s interactions with AI applications, which will become a natural part of their daily lives. As a result, gaps will appear in how younger and older generations perceive AI’s influences on society.

Likewise, AI could widen existing inequalities of opportunity if access to AI technologies—along with the high-powered computation and large-scale data that fuel many of them—is unfairly distributed across society. These technologies will improve the abilities and efficiency of people who have access to them. A person with access to accurate Machine Translation technology will be better able to use learning resources available in different languages. Similarly, if speech translation technology is only available in English, people who do not speak English will be at a disadvantage.

Further, AI applications and the data they rely upon may reflect the biases of their designers and users, who specify the data sources. This threatens to deepen existing social biases, and concentrate AI’s benefits unequally among different subgroups of society. For example, some speech recognition technologies do not work well for women and people with accents. As AI is increasingly used in critical applications, these biases may surface issues of fairness to diverse groups in society. On the other hand, compared to the well-documented biases in human decision-making, AI-based decision-making tools have the potential to significantly reduce the bias in critical decisions such as who is lent money or sent to jail.

Privacy concerns about AI-enabled surveillance are also widespread, particularly in cities with pervasive instrumentation. Sousveillance, the recording of an activity by a participant, usually with portable personal devices, has increased as well. Since views about bias and privacy are based on personal and societal ethical and value judgments, the debates over how to address these concerns will likely grow and resist quick resolution. Similarly, since AI is generating significant wealth, debates will grow regarding how the economic fruits of AI technologies should be shared—especially as AI expertise and the underlying data sets that fuel applications are concentrated in a small number of large corporations.

To help address these concerns about the individual and societal implications of rapidly evolving AI technologies, the Study Panel offers three general policy recommendations:

1. Define a path toward accruing technical expertise in AI at all levels of government. Effective governance requires more experts who understand and can analyze the interactions between AI technologies, programmatic objectives, and overall societal values. Absent sufficient technical expertise to assess safety or other metrics, national or local officials may refuse to permit a potentially promising application. Or insufficiently trained officials may simply take the word of industry technologists and green light a sensitive application that has not been adequately vetted. Without an understanding of how AI systems interact with human behavior and societal values, officials will be poorly positioned to evaluate the impact of AI on programmatic objectives.

2. Remove the perceived and actual impediments to research on the fairness, security, privacy, and social impacts of AI systems. Some interpretations of federal laws such as the Computer Fraud and Abuse Act and the anti-circumvention provision of the Digital Millennium Copyright Act are ambiguous regarding whether and how proprietary AI systems may be reverse engineered and evaluated by academics, journalists, and other researchers. Such research is critical if AI systems with physical and other material consequences are to be properly vetted and held accountable.

3. Increase public and private funding for interdisciplinary studies of the societal impacts of AI.

As a society, we are underinvesting resources in research on the societal implications of AI technologies. Private and public dollars should be directed toward interdisciplinary teams capable of analyzing AI from multiple angles. Research questions range from basic research into intelligence to methods to assess and affect the safety, privacy, fairness, and other impacts of AI.

Questions include: Who is responsible when a self-driven car crashes or an intelligent medical device fails? How can AI applications be prevented from unlawful discrimination? Who should reap the gains of efficiencies enabled by AI technologies and what protections should be afforded to people whose skills are rendered obsolete? As AI becomes integrated more broadly and deeply into industrial and consumer products, it enters areas in which established regulatory regimes will need to be adapted to AI innovations or in some cases fundamentally reconfigured according to broadly accepted goals and principles.

The approach in the United States to date has been sector-specific, with oversight by a variety of agencies. The use of AI in devices that deliver medical diagnostics and treatments is subject to aggressive regulation by the Food and Drug Administration (FDA), both in defining what the product is and specifying the methods by which it is produced, including standards of software engineering. The use of drones in regulated airspace falls under the authority of the Federal Aviation Administration (FAA). For consumer-facing AI systems, regulation by the Federal Trade Commission (FTC) comes into play. Financial markets using AI technologies, such as in high-frequency trading, come under regulation by the Security Exchange Commission (SEC).

In addition to sector-specific approaches, the somewhat ambiguous and broad regulatory category of “critical infrastructure” may apply to AI applications. The Obama Administration’s Presidential Policy Directive (PPD) 21 broadly defines critical infrastructure as composed of “the assets, systems, and networks, whether physical or virtual, so vital to the United States that their incapacitation or destruction would have a debilitating effect on security, national economic security, national public health or safety, or any combination thereof.” Today, an enterprise does not come under federal regulation solely by falling under that broad definition. Instead, the general trend of federal policy is to seek regulation in sixteen sectors of the economy.

As regards AI, critical infrastructure is notably defined by the end-user application, and not the technology or sector that actually produces AI software. Software companies such as Google, Facebook, and Amazon have actively lobbied to avoid being designated as critical to the economy, arguing that this would open the door to regulation that would inevitably compromise their rapid product development cycles and ability to innovate. Nonetheless, as the companies creating, operating, and maintaining critical infrastructure use AI, interest will grow in regulating that software. Some existing regulatory regimes for software safety (for example, the FDA’s regulation of high consequence medical software) require specific software engineering practices at the developer level. However, modern software systems are often assembled from library components which may be supplied by multiple vendors, and are relatively application-independent. It doesn’t seem feasible or desirable to subject all such developers to the standards required for the most critical, rare applications. Nor does it seem advisable to allow unregulated use of such components in safety critical applications. Tradeoffs between promoting innovation and regulating for safety are difficult ones, both conceptually and in practice. At a minimum, regulatory entities will require greater expertise going forward in order to understand the implications of standards and measures put in place by researchers, government, and industry.

Policy and legal considerations

While a comprehensive examination of the ways artificial intelligence (AI) interacts with the law is beyond the scope of this inaugural report, this much seems clear: as a transformative technology, AI has the potential to challenge any number of legal assumptions in the short, medium, and long term. Precisely how law and policy will adapt to advances in AI—and how AI will adapt to values reflected in law and policy—depends on a variety of social, cultural, economic, and other factors, and is likely to vary by jurisdiction.

American law represents a mixture of common law, federal, state, and local statutes and ordinances, and—perhaps of greatest relevance to AI—regulations. Depending on its instantiation, AI could implicate each of these sources of law. For example, Nevada passed a law broadly permitting autonomous vehicles and instructed the Nevada Department of Motor Vehicles to craft requirements. Meanwhile, the National Highway Transportation Safety Administration has determined that a selfdriving car system, rather than the vehicle occupants, can be considered the “driver” of a vehicle. Some car designs sidestep this issue by staying in autonomous mode only when hands are on the wheel (at least every so often), so that the human driver has ultimate control and responsibility. Still, Tesla’s adoption of this strategy did not prevent the first traffic fatality involving an autonomous car, which occurred in June of 2016. Such incidents are sure to influence public attitudes towards autonomous driving. And as most people’s first experience with embodied agents, autonomous transportation will strongly influence the public’s perception of AI.

Driverless cars are, of course, but one example of the many instantiations of AI in services, products, and other contexts. The legal effect of introducing AI into the provision of tax advice, automated trading on the stock market, or generating medical diagnoses will also vary in accordance to the regulators that govern these contexts and the rules that apply within them. Many other examples of AI applications fall within current non-technology-specific policy, including predictive policing, non-discriminatory loans, healthcare applications such as eldercare and drug delivery, systems designed to interact with children (for example, autonomous tutoring systems are required to respect laws in regard to balanced handling of evolution vs. intelligent design), and interactive entertainment. Given the present structure of American administrative law, it seems unlikely that AI will be treated comprehensively in the near term. Nevertheless, it is possible to enumerate broad categories of legal and policy issues that AI tends to raise in various contexts.

Privacy

Private information about an individual can be revealed through decisions and predictions made by AI. While some of the ways that AI implicates privacy mirror those of technologies such as computers and the internet, other issues may be unique to AI. For example, the potential of AI to predict future behavior based on previous patterns raises challenging questions. Companies already use machine learning to predict credit risk. And states run prisoner details through complex algorithms to predict the likelihood of recidivism when considering parole. In these cases, it is a technical challenge to ensure that factors such as race and sexual orientation are not being used to inform AI-based decisions. Even when such features are not directly provided to the algorithms, they may still correlate strongly with seemingly innocuous features such as zip code. Nonetheless, with careful design, testing, and deployment, AI algorithms may be able to make less biased decisions than a typical person.

Anthropomorphic interfaces increasingly associated with AI raise novel privacy concerns. Social science research suggests people are hardwired to respond to anthropomorphic technology as though it were human. Subjects in one study were more likely to answer when they were born if the computer first stated when it was built. In another, they skipped sensitive questions when posed by an anthropomorphic interface. At a basic level lies the question: Will humans continue to enjoy the prospect of solitude in a world permeated by apparently social agents “living” in our houses, cars, offices, hospital rooms, and phones? Innovation policy

Early law and policy decisions concerning liability and speech helped ensure the commercial viability of the Internet. By contrast, the software industry arguably suffers today from the decision of firms to pivot from open and free software to the more aggressive pursuit of intellectual property protections, resulting in what some have termed patent “thickets.” Striking the proper balance between incentivizing innovation in AI while promoting cooperation and protection against third party harm will prove a central challenge. Liability (civil)

As AI is organized to directly affect the world, even physically, liability for harms caused by AI will increase in salience. The prospect that AI will behave in ways designers do not expect challenges the prevailing assumption within tort law that courts only compensate for foreseeable injuries. Courts might arbitrarily assign liability to a human actor even when liability is better located elsewhere for reasons of fairness or efficiency. Alternatively, courts could refuse to find liability because the defendant before the court did not, and could not, foresee the harm that the AI caused. Liability would then fall by default on the blameless victim. The role of product liability—and the responsibility that falls to companies manufacturing these products— will likely grow when human actors become less responsible for the actions of a machine.

Liability (criminal)

If tort law expects harms to be foreseeable, criminal law goes further to expect that harms be intended. US law in particular attaches great importance to the concept of mens rea—the intending mind. As AI applications engage in behavior that, were it done by a human, would constitute a crime, courts and other legal actors will have to puzzle through whom to hold accountable and on what theory.

Agency

The above issues raise the question of whether and under what circumstances an AI system could operate as the agent of a person or corporation. Already regulatory bodies in the United States, Canada, and elsewhere are setting the conditions under which software can enter into a binding contract. The more AI conducts legally salient activities, the greater the challenge to principles of agency under the law.

Certification

The very notion of “artificial intelligence” suggests a substitution for human skill and ingenuity. And in many contexts, ranging from driving to performing surgery or practicing law, a human must attain some certification or license before performing a given task. Accordingly, law and policy will have to—and already does—grapple with how to determine competency in an AI system. For example, imagine a robotics company creates a surgical platform capable of autonomously removing an appendix. Or imagine a law firm writes an application capable of rendering legal advice. Today, it is unclear from a legal perspective who in this picture would have to pass the medical boards or legal bar, let alone where they would be required to do so.

Labor

As AI substitutes for human roles, some jobs will be eliminated and new jobs will be created. The net effect on jobs is ambiguous, but labor markets are unlikely to benefit everyone evenly. The demand for some types of skills or abilities will likely drop significantly, negatively affecting the employment levels and wages of people with those skills. While the ultimate effects on income levels and distribution are not inevitable, they depend substantially on government policies, on the way companies choose to organize work, and on decisions by individuals to invest in learning new skills and seeking new types of work and income opportunities. People who find their employment altered or terminated as a consequence of advances of AI may seek recourse in the legislature and courts. This may be why Littler Mendelson LLP— perhaps the largest employment law firm in the world—has an entire practice group to address robotics and artificial intelligence.

Taxation

Federal, state, and local revenue sources may be affected. Accomplishing a task using AI instead of a person can be faster and more accurate—and avoid employment taxes. As a result, AI applications could increasingly shift investment from payroll and income to capital expenditure. Depending on a state budget’s reliance on payroll and income tax, such a shift could be destabilizing. AI may also display different “habits” than people, resulting in still fewer revenue sources. The many municipalities relying on income from speeding or parking tickets will have to find alternatives if autonomous cars can drop people off and find distance parking, or if they are programmed not to violate the law. As a result, government bodies trying to balance their budgets in light of advances in AI may pass legislation to slow down or alter the course of the technology.

Politics

AI technologies are already being used by political actors in gerrymandering and targeted “robocalls” designed to suppress votes, and on social media platforms in the form of “bots.” They can enable coordinated protest as well as the ability to predict protests, and promote greater transparency in politics by more accurately pinpointing who said what, when. Thus, administrative and regulatory laws regarding AI can be designed to promote greater democratic participation or, if ill-conceived, to reduce it. This list is not exhaustive and focuses largely on domestic policy in the United

States, leaving out many areas of law that AI is likely to touch. One lesson that might be drawn concerns the growing disconnect between the context-specific way in which AI is governed today and a wider consideration of themes shared by AI technologies across industries or sectors of society. It could be tempting to create new institutional configurations capable of amassing expertise and setting AI standards across multiple contexts. The Study Panel’s consensus is that attempts to regulate “AI” in general would be misguided, since there is no clear definition of AI (it isn’t any one thing), and the risks and considerations are very different in different domains. Instead, policymakers should recognize that to varying degrees and over time, various industries will need distinct, appropriate, regulations that touch on software built using AI or incorporating AI in some way. The government will need the expertise to scrutinize standards and technology developed by the private and public sector, and to craft regulations where necessary.

Guidelines for the future

Faced with the profound changes that AI technologies can produce, pressure for “more” and “tougher” regulation is inevitable. Misunderstanding about what AI is and is not, especially against a background of scare-mongering, could fuel opposition to technologies that could benefit everyone. This would be a tragic mistake. Regulation that stifles innovation, or relocates it to other jurisdictions, would be similarly counterproductive.

Fortunately, principles that guide successful regulation of current digital technologies can be instructive. A recent multi-year study comparing privacy regulation in four European countries and the United States, for example, yielded counter-intuitive results. Those countries, such as Spain and France, with strict and detailed regulations bred a “compliance mentality” within corporations, which had the effect of discouraging both innovation and robust privacy protections. Rather than taking responsibility for privacy protection internally and developing a professional staff to foster it in business and manufacturing processes, or engaging with privacy advocates or academics outside their walls, these companies viewed privacy as a compliance activity. Their focus was on avoiding fines or punishments, rather than proactively designing technology and adapting practices to protect privacy.

By contrast, the regulatory environment in the United States and Germany, which combined more ambiguous goals with tough transparency requirements and meaningful enforcement, were more successful in catalyzing companies to view privacy as their responsibility. Broad legal mandates encouraged companies to develop a professional staff and processes to enforce privacy controls, engage with outside stakeholders, and to adapt their practices to technology advances. Requiring greater transparency enabled civil society groups and media to become credible enforcers both in court and in the court of public opinion, making privacy more salient to corporate boards and leading them to further invest in privacy protection.

In AI, too, regulators can strengthen a virtuous cycle of activity involving internal and external accountability, transparency, and professionalization, rather than narrow compliance. As AI is integrated into cities, it will continue to challenge existing protections for values such as privacy and accountability. Like other technologies, AI has the potential to be used for good or nefarious purposes. This report has tried to highlight the potential for both. A vigorous and informed debate about how to best steer AI in ways that enrich our lives and our society, while encouraging creativity in the field, is an urgent and vital need. Policies should be evaluated as to whether they democratically foster the development and equitable sharing of AI’s benefits, or concentrate power and benefits in the hands of a fortunate few. And since future AI technologies and their effects cannot be foreseen with perfect clarity, policies will need to be continually re-evaluated in the context of observed societal challenges and evidence from fielded systems.

As this report documents, significant AI-related advances have already had an impact on North American cities over the past fifteen years, and even more substantial developments will occur over the next fifteen. Recent advances are largely due to the growth and analysis of large data sets enabled by the Internet, advances in sensory technologies and, more recently, applications of “deep learning.” In the coming years, as the public encounters new AI applications in domains such as transportation and healthcare, they must be introduced in ways that build trust and understanding, and respect human and civil rights. While encouraging innovation, policies and processes should address ethical, privacy, and security implications, and should work to ensure that the benefits of AI technologies will be spread broadly and fairly. Doing so will be critical if Artificial Intelligence research and its applications are to exert a positive influence on North American urban life in 2030 and beyond. Note: Article closes with a short history of AI, which was redacted. There are other sources available which show this.

[end article]

Dawkins and 'potential people'

2015-04-04T13:10:00.000-04:00

Richard Dawkins thinks we're better off than a very peculiar kind of abstraction.

So here's a provocative quote from Dawkins, and not the normal "I'm-against-all-religion" kind either:

“We are going to die, and that makes us the lucky ones. Most people are never going to die because they are never going to be born. The potential people who could have been here in my place but who will in fact never see the light of day outnumber the sand grains of Arabia. Certainly those unborn ghosts include greater poets than Keats, scientists greater than Newton. We know this because the set of possible people allowed by our DNA so massively exceeds the set of actual people. In the teeth of these stupefying odds it is you and I, in our ordinariness, that are here.We privileged few, who won the lottery of birth against all odds, how dare we whine at our inevitable return to that prior state from which the vast majority have never stirred?” -Richard Dawkins, Unweaving the Rainbow.

This whole concept of 'potential people' having value is somewhat strange, when you think about it. I mean, really, are we saying anything at all when we talk about potential people? Can we really compare ourselves with an abstraction, a potential person, that, by stipulation of the claim, does not exist?

Suppose we did compare ourselves with said -- can we meaningfully say we are any better off than that which won't exist? Couldn't we also we we are always worse off than they, since they never suffered, but all of us inevitably do? It looks equally appropriate either way -- which make me suspicious that no comparison is really going on.

Now and then I note that Kant was friendly to this sort of talk about 'potential persons', and used the notion as a claim against the morality of abortion. In short, Kant held that living things have species-specific 'anlage' or "predispositions" that express themselves appropriately in given circumstances, giving rise to different kinds. Humans are no exception, the argument would go, especially since we must be seen as having souls from the moment of conception, and thus predispositions to humanity and personality.

So too, the pious affirm the value of potential people in an additional way: as reason to "go forth and multiply." Apparently moving as many as one possibly can from potentiality to actuality is especially pleasing to God, as religious birth demographics show.

Potential people -- such a strange addition to one's metaphysical furniture!

O.

REFERENCES

[image] "Connecting with potential employers on Linked-in" (Accessed 4/4/15)

Freeman Dyson's Strange Skepticism on Climate Change

2015-01-26T21:43:00.002-05:00

Sometimes being an out-of-the-box thinker has its downsides.

Famous physicist Freeman Dyson was recently interviewed about his climate change skepticism via email by Steve Connor, a respected science journalist for The Independent. I thought the exchange was fascinating, and highlights interesting flaws in how even an unquestionably great scientist can fail to understand the Philosophical underpinnings of how science assesses evidence for supporting (or falsifying) conclusions.

For example, I thought this was a very good question on the part of Connor:

"Isn't it a bit risky for me and the rest of the general public to dismiss this vast canon of climate science as just "fuss" about global warming when all I've got to go on is a minority opinion? "

The journalist (and I) think the answer is clearly yes -- it is risky; but, Dyson apparently thinks the answer is "no".

It was also interesting to look at Dyson's actual arguments on why experts get it wrong. Here is one selection from Dyson:

"My impression is that the experts are deluded because they have been studying the details of climate models for 30 years and they come to believe the models are real. After 30 years they lose the ability to think outside the models. And it is normal for experts in a narrow area to think alike and develop a settled dogma. The dogma is sometimes right and sometimes wrong. In astronomy this happens all the time, and it is great fun to see new observations that prove the old dogmas wrong."

One of the unstated premises in his argument is: "The more one looks at data and models the more likely one is to become 'deluded' about the subject at hand." So much for being able to learn by studying things carefully and at length for 30 years! This unstated premise is false, and is easily shown to be so on empirical grounds. Contra Dyson, perhaps an alternative reason that experts come to think the models are real after much study is because of the proper way to assess the evidence at hand. Compare the following: It's hard to think outside the model that stars are self-luminous gaseous spheroidal celestial bodies of great mass which produces energy by means of nuclear fusion reactions; because, well, all the evidence at hand shows us that this is really what they are!

Elsewhere in the article, Dyson demurs he's not an expert, and will not talk about details; but, the methods of study are publicly accessible for all to review, and the details (i.e. the data) are also readily available. Compare this to a detective that decides who the murderer is, but who will not talk about the details of the crime scene when questioned by other detectives. The details are what matters!

Dyson's comments on "settled dogma" are also quite strange. Is it just luck that sometimes the dogma is right and sometimes wrong? Of course not. Compare the following claim about desert climates: "Sometimes it rains and sometimes it's sunny." Indeed, but how often it rains as compared to how often it's sunny really matters. Likewise, how often a large consensus of scientists from multiple fields are right on a shared subject, and how often a large consensus of scientists from multiple fields are wrong on a shared subject really matters (as John Oliver points out in a very funny skit.) That is conveniently not noted by Mr. Dyson, other than to say the arguments have become heavily politicized, and thus not fairly reported in the media. (This later reasoning of Mr Dyson is an ad hominem fallacy, by the way.)

There were other failures of evidence-based thinking on Dyson's part too, but I though I'd go after the easy ones to see. Overall, being an out-of-the-box thinker can help in generating creative insights, but it can also hamper one's ability to assess confirmatory and/or invalidating evidence, especially when someone relies on personal intuition at the expense of evidentiary thinking.

Mars and 3D Building Printing

2014-07-04T13:38:00.002-04:00

This humble beginning of printing houses here on Earth is almost

certainly the mechanism we'll use on Mars to print buildings.

This company used cement, but also a mixture of recycled materials, but the recycled materials were used because they are cheap. However, the Martian soil is even cheaper, as in free, and already in a form that's easy to collect: "The dust that covers the surface of Mars is fine like talcum powder. Beneath the layer of dust, the Martian crust consists mostly of volcanic basalt rock. The soil of Mars also holds nutrients such as sodium, potassium, chloride and magnesium." [1] And free materials with handy construction properties is just what is needed for such a giant 3D printer as seen in the video above. Scientists have already considered this possibility, and even with some pre-plans (video) [2], but somehow seeing what this Chinese contractor is doing makes the prospect much more real, indeed fully viable, since it's already actually being done.

Although the contractor above built a giant, custom 3D printer for his needs, the sales trend of mass manufacturing of 3D printers is already going up at a geometric rate, as this graph shows [3]:

The reason for such a sales increase is that people are figuring out how to apply these printers to various tasks at hand. Once the abilities of these "additive manufacturing" machines are understood, printers of scale will be built for large tasks, especially for buildings, since the process from CAD software to 3D printer is becoming so smooth, and since the cost factor is greatly reduced. Such a positive cost curve is driving a huge growth in industry as this (clickable) graph shows [4]:

I remember reading about the colonization of Mars in a book some years ago, whereby lots of prepackaged buildings and supplies were dropped on Mars months before astronauts ever arrived. At the time the book was written, it made perfect sense, though it depended on an Earth-tethered space elevator being already in place to cheaply move the materials into low earth orbit, which gets around the huge fuel problem for getting things into space at all. Sadly, it appears that a space elevator is not practical even if, against all odds, we could build one. But 3D printers solve this problem, since much of the infrastructure can be built on site.

My belief is that a series of small 3D printers will be sent to Mars, and these small printers will build the actual large printers necessary (w/ video) to produce the final infrastructure product. Yes, it is indeed possible to print 3D printers with a 3D printer, which is the full manufacturing circle -- a device can replicate itself. For example, The RepRap is an open source printer that does just that, and there's no reason that even larger 3D printers on Mars couldn't do the same, printing all the parts that make themselves up, and then having robots assemble the parts .

O.

REFERENCES

[image] "3D printers print ten houses in 24 hours" YouTube (Accessed 7/4/2014)

[1] "What is Mars Made Of?" Space.com (Accessed 7/4/2014).

[2] "3D Printing Houses on Mars" FutureScape on scienceChannel.com (Accessed 7/4/2014)

[3] "Solid Print" The Economist 4/21/2012 (Accessed 7/4/2014)

[4] "The Rise of 3D Printing in Manufacturing" Distribute: Tributes Blog for Industrial Distributors 4/7/2013 (Accessed 7/4/2014)

Rethinking Abortion in Light of Advancing Technology

2014-04-08T19:13:00.000-04:00

Advances in technology will eventually change how one prioritizes which ethical "rights" get invoked for or against having an abortion.
{ Audio .mp3 (7 min.) of this essay } For my Ethics class I regularly re-read Mary Ann Warren's 1973 article, "On the Moral and Legal Status of Abortion."[1] Although it is well argued, I can't agree with every sub-conclusion she draws which would be required to justify her overall position -- hardly a surprise, of course, given my pious commitments.

In a postscript to the article, she attempts to show that her argument for the moral permissibility of abortion does not commit her to infanticide. Why not? Because after the infant is born, "it does mark the end of its mother's right to determine its fate." I have two points of disagreement with her on this matter of infanticide -- one minor, the other more substantial, but which is somewhat related to the minor issue.

First, I have never been clear on where alleged moral "rights" come from, at least if there is no all-knowing issuer and (eventually) absolute enforcer of those rights (otherwise known as God). In contrast, political rights are far more easy to understand and apply: Find the king, or the Constitution, or some other governmental authority, and then draw some sort of reference and subsequent enforcement from there. So my minor disagreement with Warren is that talk of moral rights only introduces further confusion into the abortion debate.

Second, even if one were to acknowledge some sort of discernible rights being affirmed or violated, I was curious about how the following aside from Warren would interplay with such rights:

"Indeed if abortion could be performed without killing the fetus, [the mother] would never possess the right to have the fetus destroyed, for the same reasons that she has no right to have an infant destroyed."

What might it mean to perform an abortion without destroying a fetus?

At first glance we might worry that just as murdering someone without killing them is impossible, so committing an abortion without destroying the fetus is likewise, for semantic reasons, impossible. But this is not quite a correct understanding of the term, because the very word "abortion" just means the deliberate termination of a human pregnancy, and does not, in addition, also mean the deliberate termination of a fetus's life. As we currently practice it, the act of abortion indeed causes the termination of a fetus's life, but that is merely an association due to our poor technology, not due to the prior logically entailing letter. Compare our use of the word "surgery" today as compared to times past. In the past, surgery always caused pain, but today we are fortunate to know that the association of these two terms is not one of logical entailment, as every anesthesiologist can attest.

With this semantic confusion behind us, we are now in a position to think about abortions, but without fetal termination. Perhaps we can imagine a specialized vat whereby we place a fetus within so as to grow it to viability. Advances in robotic surgery would allow doctors to remove the whole placenta quickly enough to

support the oxygen and nutrient environment which keeps the fetus viable, and then to reattach it to the artificial vat support system. In this case the woman would have terminated her pregnancy (accurately called an "abortion") but the fetus would still remain viable. Or again, perhaps the vat technology is too difficult a feat, but advances in biology allow a transplantation of just a small portion of the placenta, along with its accompanying fetus. Likewise, per as earlier, we would have terminated the pregnancy, but with the advantage of the fetus remaining viable.

In her postscript, Warren supplies two arguments on why infanticide is wrong (1) for reasons analogous to those which make it wrong to want to destroy natural resources or great works of art; or (2) for reasons whereby people value infants -- such as when foster parents who would want the infant would be deprived, or when greater society, valuing infants and willing to step up and support them, finance orphanages through the tax base. However, under advanced technology circumstances, these same issues would apply to the woman losing her "right" to commit an abortion, were the growth vat or the transplant biology advanced enough to remove the infant from the woman. Using Warrens own reasoning, just as the woman does not control the right to commit infanticide after the birth, neither would the woman control the right of feticide in utero.

Warren wants to say that the rights of actual people trump the rights of potential people, but I am unclear which rights are being mentioned. My suspicion is that there are conditions where the right of the woman's quality of life could very well be subordinate to the rights of a fetus to have life at all. Suppose that the surgery were no more troublesome than having a mole removed, or taking a few hours out of one's day for an anesthetic nap (for surgery), similar to colonoscopy procedure. Under these conditions there would be minimal quality of life degradation. Even if one acknowledges the presence of moral rights, there must be a hierarchy to these rights to make them workable, as both scholars and jurisprudence practitioners of legal rights have recognized.

Earlier in her article Warren wants to suggest that an actual person's rights (in this case the mother) always trump a potential person's rights (the fetus). I don't see why this should be accepted a priori. Indeed, the mother should not be presumed as the only actual person with rights in place. Instead, I suggest that it is the empirical circumstances and consequences which allow us to formulate the hierarchy of already-acknowledged rights. If one grants this suggestion, the consequences of the mother's degradation of quality of life could eventually be so low in the advanced technology cases mentioned that one should assess the fetus's right to life as super-ordinate over the mother's right to quality of life. If so, then I conclude that we shall soon be rethinking abortion in light of advancing fetal support technology.

O.

REFERENCES

Images: Header image taken from article, Soraya Chemaly "What Do Artificial Wombs Mean for Women?" 2/23/2012 RH Reality Check Blogsite (Accessed 4/8/2014). Inset image taken from Green Diary - Green Living Blogsite. (Accessed 4/8/2014)

[1] Ann Warren "On the Moral and Legal Status of Abortion" [.pdf] The Monist: An International Quarterly Journal of General Philosophical (Peru, IL, 1973).

Churches, Science, and "Truth" Claims

2014-02-19T07:00:00.000-05:00

'True information' from religious prophets about the present and future affairs of human civilization hasn't been very forthcoming as of late.

While at a theology conference, I heard a well-received bible scholar claim that the mission of the church is "truth telling." Alas, if only it were true. The problems with such an optimistic view of what information churches (or religious groups in general) supposedly dispense are many.

First, as is well attested in history, churches have made empirically false claims about the present state of affairs, and these being supposedly based on some exclusive channel of information (something called, "special revelation") For example, the Roman Catholic Church during the Medieval times is well known for clashing with Galileo on the structure of the solar system. Their theologians had apparently gotten it right (via special revelation to a Pope) that the Earth, not the Sun, was at the center. But that didn't turn out to be so accurate. As a more recent example, the Seventh Day Adventists and conservative baptist churches worry themselves (unnecessarily, of course) about the earth being 6,000 years old and about why Evolution must be false, though these are (bad) deductions from certain woodenly literal ways of reading the bible. Thus, their mistake is to draw deductions from (allegedly) special revelatory information encoded into biblical manuscripts, information imparted by God to the original authors on scientific topics. Those geology and biology claims are not turning out well, either, for conservative churches.

Second, even if some churches have a set of specially revealed truths, their members do not have a trustworthy method for verifying such truths in the public arena. Unlike Science, there are no reproducible methods, nor ways to quantify evidence for the various churches' claims for truth. In fact, when empirical claims are made, such as for the efficacy of prayer for healing diseases, every well-structured study has shown no cause-effect links between these claims and disease healing rates. (The most famous and well-designed one even showed a lower than expected link for heart patients.) To be accurate, however, some prayers can have benevolent effects on people's health, since they are likely (from what we can tell) particular (and benevolent) occurrences of placebo effects, which is not necessarily a bad thing.

Third, leaders of churches seem especially worried about ethical truths (even more so when these concern what people do when naked.) But ethical truths are most acutely the kinds which are controversial and nebulous everywhere; for, they are not open, or at least not obviously open, to resolution on scientific grounds. (There are no Geiger counters for goodness or wickedness, for example. This is most fortunate for politicians.) But that leaders of churches would camp on ethical issues is understandable, since churches have been embarrassed by making what turned out to be false claims about empirical truths in the past, as was noted earlier. Happily for preachers and spiritual advisers everywhere, it's far more difficult to show that certain ethical principles are outright false (as compared to empirical claims), if such can even be shown for ethical claims at all.

Finally, in terms of actionable future information, note how in the present time that no revelation-filled prophets have arisen among various religious leaders to offer solutions to pressing contemporary problems (i.e., as regards cheap engineering techniques for world energy needs; safe methods for genetically modifying plants for plentiful food supply, etc.) Surely a great alleviation of suffering could have already been accomplished if key aspects of (almost-here-anyway) technologies would have been revealed from a few prophets reporting information communicated from the On High. Furthermore believers claim that in biblical times prophets often foretold dire political and economic events. Contrast this with foretelling today -- although two or three economists were (after the fact) found on record to have been clanging a warning cymbal about the possibility of the current Great Recession, every Christian and Islamic group that I'm aware of was caught flat-footed and suffered great financial loss, as did virtually everyone else. Thus, the very religious organizations which hold the possibility and precedent of prophets appearing always seem to be fresh out of them when the need is greatest!

Therefore, as an overall assessment, it is hardly surprising that people competent in assessing evidence find such pious announcements concerning "truth telling" (whether of the present or future variety) by religious leaders unconvincing. Granted, sometimes truths are uttered by the pious. But holding positions, even correct positions, for non sequitur or just plain bad reasons is either an indication of 1) luck, 2) ignorance, or social or political maneuverings--and that's a truth worth noting!

O.

2014-02-16T12:19:00.000-05:00

Soon it'll be the default for everyone, and for free

Four, standard women of typical physical charisma were given a professional model shoot and then Photoshopped using industry standard techniques. The results were (not surprisingly) beautiful idealizations from what they originally looked like. (video link).

I had a couple of thoughts strike me on the process. 1) One woman asked, "Why would anyone want to do this?" -- i.e., want to present women in this idealized way. The answer is pretty straightforward: because it makes companies money -- lots of it. As just a short summary of the fashion biz:

The global fashion industry is estimated to be worth over 1 Trillion Euro, or about 2% of the value of the world economy. To put it in context, the global pharmaceutical industry, which supplies all the medicines in the world, is valued at about €600 Billion, making it just over half the size of the fashion industry![1]

2) What if, in the (near) future, anyone could easily download a Google glasses app that automatically and instantaneously performs this task, virtually, to everyone within the visual field of the observer? What would be the effects on how we view beauty? Should one actually use such an app?

O.

----------

REFERENCES

[1] "Fashion and Beauty" CarreersPortal (Accessed 2/16/14)

Uncle Philly on Indexicality

2013-12-18T16:41:00.000-05:00

O.

----------

REFERENCES

[*] Louis Doulas, "Where is Here, When is Now, Who is I: On Indexicality" Philosopher.io

Uncle Philly on A.I.

2013-12-17T15:36:00.000-05:00

Uncle Philly on Cyborgs

2013-11-30T15:50:00.000-05:00

Uncle Philly

2013-11-22T10:08:00.000-05:00

On the down side, Uncle Philly's crotchety; but, on the up side, he's worth knowing.