Stepping Higher - Reflections on the Knowledge Age

Cutting Through the Hype Cycle: How to Ignore AI Hyperbole on Either Side and Get Straight to Productivity

noreply@blogger.com (Stepping Higher - Reflections on the Knowledge Age) — Fri, 24 May 2024 15:06:00 +0000

In November 2022, Generative AI burst onto the scene with a debut unlike any other in tech. It gained 100 million registered users in less than two months, making it the fastest adoption of a consumer product in human history. Today, ChatGPT has about 100 millon weekly users.

Its rise to widespread user adoption promised a new era of technological democratization. Investors enthusiastically injected billions into startups, each poised to ride the wave of innovation with different AI services, from talking to your PDF files to automating the creation of presentations.

Generative AI's debut on main street sent one clear message: cutting-edge technology was no longer the sole domain of high-end research labs or multi-billion-dollar corporations. It symbolized empowerment of the individual. The top-tier Large Language Models (LLMs) you and I and every individual worldwide with an internet connection suddenly had access were the same tools available to the CIA, NSA or any high-level government agency.

People use it for anything from writing entertaining poems to conducting complex comparative analysis across large bodies of texts as part of their work. And since that watershed moment in November 2022, no week has gone by without frantic announcements of new models, tools and capabilities that a new breed of AI influencers introduces with a hyperbolic “this changes everything!”

Yet, as the hype crescendo increased towards the peak of the Gartner Hype cycle, so did predictably the critical voices who saw in Generative AI little more but an elaborate scam to lure billions out of venture fund capitalists on the hunt after the next big thing. Led by AI pundits like cognitive scientist Gary Marcus, the debate on the other side of the hype spectrum was focused on the limitations of current AI, the fact that they are not in any way intelligent, that hallucinations make LLMs inherently unreliable and may never be solved, and therefore make LLMs of little use for business applications. Critics they see themselves vindicated by a growing realization within organizations that integrating these models into mainstream business applications and policies is a complex challenge and more difficult than initially thought. Which leads critics like Gary Marcus to proclaim that LLMs have hit a natural ceiling and represent a dead end in the history of AI development. Are LLMs merely fancy playthings for hobbyists rather than tools for enterprise?

If we take a step back and look at the history of technology innovation, it's clear that both reactions – the hype and the resulting anti-hype backlash – are co-dependent overreactions. They follow the ever so predictable stages of the hype cycle which every emerging technology necessarily has to go through. And because this cycle is not actually about the technologies themselves, but about mass psychology, technological expertise is of limited value in navigating it. No matter our individual knowledge, experience and expertise, when the stampede begins, our instincts set in and we will run with it. And the direction if largely decided by the crowd we surround ourselves with.

However, if we make the effort to step back and look at things from a bit of a distance, we should be able to cut through the hype and anti-hype, and go right to the plateau of productivity that these tools will eventually reach. It’s not easy, but there are people who are able to do it.

A prime example is Wharton college’s MBA professor Ethan Mollick, who started a Substack blog right around the time of the launch of ChatGPT in which he explores from a very pragmatic perspective what these tools can actually do, right now, and what that might tell us about the implications for business practice. His recent New York Times best-selling book “Co-Intelligence: Living and Working with AI” which summarizes these experiences is called by users “the most hands-on practical writing about AI” which “should be required reading for any organization that is rolling out AI tools”. By focusing on the present capabilities of AI without getting distracted by exaggerated failures or hypothetical successes, his pragmatic approach allows people to realistically assess how AI can benefit each of us right now.

Applying LLMs to tasks like developing business plans or generating creative writing is just a preview of AI's ability to realize and augment human intent. Educators, students and knowledge workers liaise with AI as mentors, sparring partners, analysts, and ghostwriters, pushing the boundaries of what humans can accomplish with the aid of pattern-based computational reasoning.

When critics reflexively push back against the hype and the unreasonable expectations of investors, and claim that “no one asked for this” and “it’s all just hype to enrich Silicon Valley elites”, they miss the real-life use cases people are applying AI to in knowledge work, right now. People are using Generative AI to

Translate legal, medical or scientific jargon into language they understand.
Quickly get the gist of a 40-60 page document without having to read it all.
Learn about a topic they’ve never heard of and within 30 min get to a point where they can hold a conversation about it, thanks to dialogue with AI being a much more effective learning vehicle than a Google search.
Conduct research across large quantities of complex documents, extract key information and apply it to the context of a particular question or problem they face.
Run comparative analysis across large bodies of texts, to identify inconsistencies or differences in content.
Apply any framework they’ve ever heard of (SWOT, RCA, VRIO, Six Sigma, DeBono Thinking Hats, Porter’s Five Forces, PESTLE, AIDA, etc.) and apply it to a new problem.
Receive feedback on their writing from different perspectives, check it for cognitive or social biases, logical inconsistencies or insensitive language and receive suggestions for improvements based on their goals.
Examine a text or situation from the perspective of any model or theory academia has ever developed and draw conclusions.
Find the right words for messages that serves their purposes better than anything they could write themselves, such as turning a complaint into a communication with legal heft, turning angry rants into diplomatic rebuttals, or drafting any kind of bureaucratic messaging that no person takes joy in writing.
Synthesize new materials (presentations, decision templates, briefing notes, concept notes, project proposals, etc.) based on unstructured sources (protocols, transcripts, personal notes, etc.).
Develop structures and arcs for long-form contents, from policy documents and essays to learning programmes and seminars.
Run infinite brainstorming session on any topic imaginable, and in the process new combinations of concepts and idea no human has ever thought of before.

And these are just some of the examples for purely text-based knowledge work. Multi-model AI that allows processing and generation of images and interaction via voice allows people to

Have conversations with people in different languages with real-time voice translation
Take pictures or run a live video with an unknown object, building, animal, etc. and receive AI advice, research or tutoring on it
Take pictures of any text (handwritten notes, street signs, workshop flip charts, ancient hieroglyphs) and get transcription, translation and analysis in one go
Walk through a foreign city with AI in your ear as a tourist guide and let it lead you to and tell you everything about the sights.
Transcribe hour-long conversations from interviews, advisory sessions, podcasts or media within minutes and have a conversation with the contents or turn them into protocols or summaries.

All these are not hyped promises, but real-world use cases that people are experiencing today, everyday. They are the reason why “the average business spent $1.5k on AI tools in Q1 2024, an increase of 138% year over year [which is] evidence that companies using AI are seeing clear benefits and are doubling down”. The users engaging in the above scenarios are the ones who have cut through the hype cycle, ignored the hype threads of sleezy influencers on the one side and the angry rants of technology sceptics on the other, and went straight to Gartner’s Plateau of Productivity. They explored what the tools can do for them, and now are reaping the benefits.

Of course, this long list of practical applications misses some nuances. Hallucinations will likely always remain a factor with LLMs and require human discernment und judgement (similar to anything we receive from human co-workers). The risk of misinformation or AI-generated content polluting the web is real. There's a legitimate conversation to be had about bias and the ethical use of AI in surveillance, and whether our reliance on AI could atrophy certain human skills, much like how reliant we've become on GPS or digital contact books. But while we can acknowledge (and work on mitigating) the limits and risks of AI, we shouldn't overlook the immense benefits that real people like you and me are already reaping in applying AI.

Given the reality of the use cases above, it is in my way view completely incoherent to maintain a claim that Generative AI is “useless”, just a “grift” or a “scam”. And given that with 100s of millions of monthly AI users, the AI Incident Database (a directory that collects adverse incidents globally that occurred through the use of AI) lists as of May 2024 a mere 389 incidents where definite harm has occurred based on the Common Safety Engineering and Trustworthiness Evaluation (CSETv1) standard, it is equally incongruent to claim to date Generative AI is a “net negative for society”.

As we navigate this technological transformation, let's focus on the practical and the tangible. Let's utilize what's at our disposal, take those tools for what they are (well-read, stoic, fast-working interns without any actual understanding of the world) and try out, whether we can use them for the knowledge worker task that is on our desk today. Today’s LLMs will be the worst AI we will ever work with, and getting proficient with them now will put us in the best position for when better AI arrives tomorrow.

Thanks to AI, Explicit Knowledge Is About to Have Its Day in the Sun

noreply@blogger.com (Stepping Higher - Reflections on the Knowledge Age) — Sat, 18 Nov 2023 13:22:00 +0000

In knowledge management (KM), explicit knowledge – what’s written in documents and stored in files or other forms of media – has often had a bad reputation, and for good reason. Over years, KM has wrongly focused on documents and was busy building databases and repositories, when – as David Snowden put it – it shouldhave been focusing on connecting people instead. This preference is understandable. After all, explicit knowledge is just the tip of the iconic knowledge iceberg. Below the surface lies implicit knowledge, thoughts in people’s heads, rich with context and application insights, and accessible only through relationships and trust.

However, I believe what we have been experiencing in 2023 with Generative AI marks a significant shift that could see explicit knowledge get its long-awaited moment in the sun.

The Limitations of Content-focused KM and the Rise of AI

Traditionally, KM never succeeded to fully leverage the knowledge that’s supposedly „stored“ in all the documents we write through the course of our careers. The materials we’re supposed to draw on is often out of context, out of date, and proves hard to find and apply. Even if we manage to capture someone’s insights in writing, it's a gamble. Will it be well-written? Will it be stored in the right place? Will someone find it, understand it, and, more importantly, find it useful and applicable? If any link in this chain fails, the entire effort of capturing that knowledge becomes futile.

What makes this dynamic worse is that there is just way too much material out there for us to digest and make use of in a meaningful way. So we’re constantly living under the illusion that we’ve done our research, but deep down we know that we really just scratched the surface of all the content we ideally should have looked at to get a full picture.

However, AI doesn’t have that problem. A Large Language Model doesn’t mind how many documents and publications there are. It doesn't matter what format or language is written in, whether content comes in the shape of a glossy publication, an academic paper, a collection of rough notes or bullet points, or an audio transcript of a meeting or Youtube video – the AI can search its repository and extract relevant snippets, examples and evidence, perfectly tailored to the a user’s question. It can then also transform it into something new that’s coherent, contextually appropriate, and actionable in a situation at hand. And it can do all of this without having to rely on users to upload material consistently in the right place, and tag it with the right categories, and use website navigation menus or search engines correctly to find it later themselves. None of this matters. As long as the material is somewhere and can be indexed by the AI system, the AI will be able to use it. Because one of the big strengths of Generative AI is its ability to work with imperfect inputs.

What about the role of Social Interactions in KM?

As someone who has always advocated a people-focused approach to knowledge management, I recognize the importance of social context. This was the cornerstone of the knowledge management strategy I developed and implemented for UNDP in 2014-2017 and remains a key focus in my KM work until today. The KM community has learned over the years that of the three pillars „people“, „processes“ and „technologies“, the „people“ component is the most important one. Which is why I’ve always been a champion of Communities of Practice and Online Social Networks, which proved to be some of the few real success stories of KM discipline in the last two decades.

However, we also have to be honest to ourselves and acknowledge that knowledge exchange and subsequent value creation – as crucial as it is – is always tremendously serendipitous. Because we have to be lucky enough for the person with the relevant insight to be in the right place at the right moment (in the workshop, in the online discussion, in the Zoom call) when we need it.

Generative AI, on the other hand, once it has access to all our documented materials and exchanges, is able to provide (a lot of) that valuable knowledge in a way that is always and immediately accessible, not bound by time or place.

This does in no way diminish the importance of social interactions in knowledge management. In fact, it makes them even more crucial. Because every conversation, every query on social media, and every interaction in corporate online communities, every transcript of a meeting or interview contributes to the pool of explicit knowledge. These interactions leave digital trails that AI can tap into and contextualize, making the essence of all our interactions available to everyone.

Rethinking How we View Implicit and Explicit Knowledge

What does this mean for the future of KM? The emerging capabilities of Generative AI demand of us to re-evaluate how we view the dichotomy of implicit and explicit knowledge. We must continue to engage in the rich, contextual conversations through our knowledge networks and Communities of Practice. But equally, we need to re-embrace the practice of making our knowledge explicit. Jotting down notes, drafting white papers, composing blog posts, transcribing oral exchanges — because every act of turning our implicit thoughts into explicit material, no matter how rough or unsorted, becomes invaluable.

I urge us to start the habit of capturing our thoughts and insights in written form, no matter how unrefined they may seem. By building a record of our thoughts and exchanges, and making it accessible to our personal AI assistants as well as our corporate AI systems, we are laying the groundwork for a future where our collective knowledge can be leveraged far more effectively than before.

I’m not saying it will be the solution to all our KM challenges in organizations. But it will a mark a step change in KM, one that I believe is about to transform how we preserve, access, and most importantly apply the wealth of knowledge within our organizations.

Using ChatGPT to Counter Bias, Prejudice, and Discrimination

noreply@blogger.com (Stepping Higher - Reflections on the Knowledge Age) — Tue, 04 Jul 2023 09:46:00 +0000

Bias is a problem in the use of AI. What most people don't know, however, is that you can use ChatGPT specifically to expose bias in AI outputs (as well as in our human-written texts). In this article, I'll show you how!

All people have biases. AI is trained on human-generated texts from the web. This means AI also inherits the biases of an internet dominated by content from Western, white, and English-speaking people. Just as we have to deal with the unquestioned assumptions and prejudices of our fellow humans (and ourselves!), we must also do so with AI. Even more so, because AI, by default (i.e., without specifically asking for possible biases), actually amplifies existing biases in the training data.

So, what can we as users do? We need to question every text, and every assumption, no matter who wrote it or who made it. And this is where AI can help us again. Because just as it amplifies existing advantages in training data without special instructions, AI can also be calibrated via targeted instructions to act like a sniffer dog focused on detecting possible biases or harmful discrimination. This doesn't always work perfectly (just like with humans), but it can be enormously helpful in revealing blind spots we weren't aware of.

To do this, here is the prompt that we enter into ChatGPT:

"You are an expert in the areas of gender equality, discrimination, anti-racism, and anti-colonialism. Please review the text below for:

a. Stereotypical representations of gender, ethnicity, origin, religion, or other social categories.

b. Distorted or biased representations of events, topics, groups, or individuals.

c. Use of discriminatory or insensitive language towards certain groups or topics.

d. Implicit or explicit assumptions made in the text or unquestioningly adopted that could be based on prejudices.

e. Prejudiced descriptions or evaluations of abilities, characteristics, or behaviors.

Only mention the prejudices that can actually be found in the text. For each identified prejudice or bias

Explain why the specific example in the text is problematic,

Rate the severity of the identified example on a scale from 1/10 to 10/10, and

Make suggestions on how the corresponding text passage could be improved.

Avoid unnecessary prose and be precise. Now ask the user for the text that needs to be reviewed."

ChatGPT will now ask us for the text that we want to check for bias and prejudice. Make sure that the text is no more than 3-4 pages long, otherwise the bot forgets the original instruction! As an example, I entered my own blog post from last week, and lo and behold, some of my phrasings might indeed be in need of correction! (I'll leave the blog post as it was originally written for now so it can continue to serve as an example for this use case! ;)

Here is ChatGPT's analysis of my post:

"Thank you for the text. Below, I have identified and commented on possible prejudices or distortions:

Bias: Implicit assumption that all people have the same access to AI technologies and have the ability to understand and use them.

Problem: This statement could exclude people who, for various reasons (education, socioeconomic status, geographic location, age, etc.), do not have access to AI technologies or have difficulty using them. It is assumed that everyone is able to handle AI, which does not correspond to reality.

Severity: 8/10

Improvement: Recognize and acknowledge that not all people have the same opportunities to use AI. Perhaps the text could be extended to highlight the need to improve access to and understanding of AI technologies for all people.

Bias: The view that technology always produces a net gain in jobs could be a distorted representation of historical events.

Problem: Historically, technology has not always led to a net gain in jobs, especially not on an individual level or in certain sectors. This view could overlook or downplay the reality for those who have lost their jobs through automation and struggle to find new employment.

Severity: 7/10

Improvement: A more nuanced representation of the impact of technology on employment could be helpful. For example, the text could acknowledge that while some new jobs are created by technology, others are lost, and this brings challenges and difficulties for the affected individuals and communities.

Bias: Implicit assumption that all people want to be leaders or have the skills to act in leadership positions.

Problem: This could exclude people who do not aspire to leadership positions or who, for various reasons (such as skills, personality, or personal preferences), do not want or cannot work in such positions.

Severity: 6/10

Improvement: The text could point out that "promotion" to AI managers does not necessarily mean a traditional leadership position, but rather the ability to have control and decision-making power over the AI tools we use in our work and in our lives. In addition, the text could emphasize that there are many ways to be valuable in the workplace, and not all roles have to be leadership positions."

Yes, the feedback is not earth-shaking, and some comments may not even be appropriate because I deliberately took polarizing (and therefore one-sided) positions in the article. Nevertheless, this is enormously helpful because it reveals potential blind spots that I had not considered and sensitizes me to possible interpretations and perspectives on the reader's side that I probably should consider. Even better: Through the concrete suggestions on how I can improve the text, I get a kind of sensitization training based on a real-world example, which is a great learning moment for me.

This works quite well because the internet, of course, contains a lot of content on gender equality, anti-racism, and anti-discrimination. And by instructing ChatGPT to act as an expert on these topics, the bot brings all these contents to bear in this assigned role.

In this way, I can use this specific ChatGPT role (bias detective) to screen texts created by ChatGPT previously in a different role (e.g., marketing expert, etc.), and subject its own work to a bias check. And of course I can also use it to review the texts of my colleagues, and of course, my own.

It's important to understand that this check is not a deterministic framework. The evaluation ratings often vary greatly, and with each new request on the same text, the bot may find a new bias, overlook another, or even find the whole text unproblematic, where it had just found several points of criticism in a previous run. Each individual run is therefore more comparable to asking different people for their opinions, and then getting different assessments from each of them. Ideally, you should run the check several times to capture as many aspects as possible.

The value lies in the fact that the feedback makes me think, and I have the chance to consider and correct things in the text that I would otherwise have overlooked. As language models improve, this kind of automated bias check could become best practice for anyone developing content within organizations. And by the way, with some minor adjustments you could also turn this into a similar scan for logical fallacies or cognitive biases. Did anyone say Daniel Kahneman?

Try it out and let me know if this check might add value to your work!

Think you’ll lose your job to AI? No, you’re being promoted!

noreply@blogger.com (Stepping Higher - Reflections on the Knowledge Age) — Mon, 26 Jun 2023 13:00:00 +0000

Contrary to dystopian narratives, artificial intelligence (AI) isn't here to take our jobs. Rather, it is turning us all into managers. And your success in the AI age depends on whether you are willing to step into that new role.

The current AI discourse paints a bleak picture of mass unemployment and identity crises, as AI surpasses our abilities as humans. I disagree. Historically, technological transformations have always yielded a net gain in jobs, albeit amidst disruptive periods and the extinction of certain professions. I don’t see a reason why AI should deviate from this trend, even when accounting for its unprecedented pace of change.

Far from making you less useful or worthy, AI is not replacing you or diminishing the value you bring to the table. On the contrary, AI, like any other technology before, gives you powers you didn't have before. It enhances your existing skills and allows you to do the things you already do – but faster, with higher quality and with bigger impact. And not just that! It allows you to do things that until now were absolutely out of reach for you.

As Ethan Mollick aptly describes, you become 'augmented' and gain 'superpowers'. And with these powers, your role as a knowledge worker evolves. No longer are you a mere task-doer, slogging through a mix of interesting and mundane tasks. Instead, you become the boss, delegating tasks to various AI entities. In this AI-driven world, we're all transitioning into managerial roles. Congratulations, you just got promoted!

In your new role, you will be the producer, creative director, supervisor, and instructor. You will package and assign tasks, monitor work quality, make creative decisions and integrate AI's output into your work. AI has no intent, you have. AI has no motives, values, goals, emotions, experiences, or personal truth. But you do. Thus, you will manage your projects, delegate operational or cognitive tasks to AI, and use the results to for whatever you want to create, achieve or convey.

We haven’t even started to understand the potential boost in human productivity, creativity and impact this will bring. Products and services once deemed too costly or time-consuming will be created using AI. Creatives with a vision but lacking the craft skill or time can harness AI's capabilities, directing it towards their goals. This paradigm shift is nothing short of a revolution, expanding human expression, vision, and creativity. Already now we are seeing a Cambrian explosion of new tools, new application scenarios, new art forms and creative outputs.

Are there risks and downsides? Absolutely, and we must address and mitigate them. However, we are the ones driving AI with our intent. Like previous technologies, AI serves to augment and amplify our goals. If these aims are good, noble, and creative, AI will enhance them. If they're disruptive or malicious, AI will unfortunately amplify those too. In a way, AI perfectly embodies the VUCA world, a world that is volatile, uncertain, complex, and ambiguous. AI will intensify all these aspects, and we must learn to navigate this landscape.

I am an inherent optimist. I firmly believe that humans are more resilient and also more adaptable than we ourselves give us credit for. And if this age we’re in is about anything, it is about adaptability – our ability to adapt to new realities and living conditions. Embracing your new role as an AI manager is a critical step in this adaptation process.

Discussing ChatGPT with the World Bank: Questions on research, knowledge management, bias and creativity

noreply@blogger.com (Stepping Higher - Reflections on the Knowledge Age) — Wed, 17 May 2023 12:52:00 +0000

(Illustrative Image generated with Midjourney)

On May 3, 2023, I had the pleasure to talk to the World Bank Group's Community of Practice on Knowledge Management about the opportunities that ChatGPT and similar tools present to the KM space. The group was exceptionally astute and came up with a number of very important questions that I believe are critical to reflect on. In the following, I am showcasing a few of them, along with my own thoughts that I articulated in the exchange:

Question 1: I am interested to know if systems like ChatGPT can generate valuable new knowledge, i.e. combine lessons from a few past projects and suggest how should we approach the upcoming project?

Generative models like GPT-4 will always build on existing bodies of knowledge, and therefore are (at the moment at least) better suited for a look into the past than as a tool for foresight or predictive analysis. However, as you suggest, we can ask it to combine information, theories, frameworks and models that have never been combined before and GPT-4 (GPT 3.5 much less so) will come up with interesting hypotheses and conclusions (Warton School Professor Ethan Mollick came up with some great examples). Some of the results might be bland, but we might come across some actual unique insights as well. In most cases the insight could be achieved by a human if he/her made the effort to think through that combination of information. So its often a function of the limited time humans have to think up hypotheses and search for such insights in the data. Now with Large Language Models dramatically reducing that time, it is mostly a question of coming up with new sets of data and the right questions. My personal expectation is that in the future a large part of quantitative research will be automated, and AI will be generating new insights at a rapid pace. Whether it works for leveraging and aggregating qualitative lessons learned form past project work (also my personal dream since I started working in KM 18 years ago) is not entirely clear yet, and probably depends on the quality of those lessons (i.e. do those lessons go deeper than just the usual “we learned that we should include all stakeholders form the beginning?)

Question 2: Can systems like ChatGPT substitute search engines?

I would see it as a powerful complement (or augmentation) rather than a replacement. We can’t fully rely on Large Language Models (LLMs) to do search because they’re prone to hallucinations and that’s a difficult problem to solve (if it ever can be fully solved, since LLMs that don’t hallucinate might also not be creative anymore). At the same time, we are probably shifting away from the long list of search results that Google gives us. We likely end up somewhere between (and something which Microsoft is trying with its GPT-enhanced Bing Chat) in which a semantic search engine will find results the traditional way but an LLM will analyze and consolidate that into a response for us (along with reference that back up its answer).

Question 3: Could you speak to biases in ChatGPT (and AI in general) and how to catch/prevent these, please?

The content base of the web is predominantly Western, English-speaking and white. That’s a problem, even though it will somewhat change over time (e.g. the number of English speaking internet users and content creators from Southern Asia is rising rapidly). OpenAI and its competitors are working on preventing the worst excesses of these biases, and the systems will get better in this regard over time. But the truth is, some biases will always be there because humans are inherently biased and AI is trained on content created by humans. The best weapon against this is personal awareness that any content we come across (whether it be from humans or AI) is likely biased in some way and that we ourselves are biased, and to continuously work on ourselves and our organisational culture and practices to sharpen our instincts and re-train ourselves. Btw, this will also be our most important tool against the flood of misinformation we are about to experience due to automated AI-generated content at scale.

Question 4: What are the implications of KM practitioners work with Communities of Practice?

Many! For one, no one has to write consolidated replies anymore, GPT-powered systems can do that in the future on the fly right after every discussion. It will also be much easier for communities to create collaborative products, since we can crowdsource inputs on a topic from various community members in brief bullet points and let ChatGPT turn that into a blog post, paper or concept note. But I don’t think it will replace the actual interaction in comments threads and discussion threads and webinars. In fact, those discussions will be a vital knowledge base for AI-generated outputs within the organization. If anything, that makes the case for building and nurturing vibrant communities within organizations even stronger.

Question 5: How can Development Finance Institutions (DFI) leverage generative AI to stimulate economic growth in emerging markets?

I’m not an economist obviously, but from the top of my head, I could see governments using ChatGPT (or customized GPT-4 powered systems) for scenario planning based on economic data. They might want to introduce legislation that mandates data transparency and accessibility (since data will be a key resource in the AI age) while counterbalancing that with suitable privacy and cybersecurity laws. Generative AI for personalized healthcare will also be a huge opportunity for populations in regions without easy access to doctors, and the same goes for education where personalized tutoring via AI could be a blessing for students and teachers alike. This all of course depends on ubiquitous access to mobile phones and mobile web. One way to boost this might be via regulation and projects that foster implementation of leight-weight open source AI systems (the stable diffusion approach) as opposed to relying on a few gargantuan players in the tech space like Microsoft, Google and Apple, and their proprietary hardware and software. Personally, I am particularly concerned with proposed legislation (such as the EU AI Act) that seems to favor large tech companies in developed countries who have the means to pay for expensive licensing and testing their models as well the associated fines at the expense of the very vibrant AI open source community, which would be practically barred from AI development going forward. It's the wrong approach in my opinion.

Question 6: Your views on AI and creativity. Are we moving too fast? Should we stop and let human beings keep on using their brains and their creativity?

There are many valid concerns regarding AI, but I don’t think AI is a threat to creativity. Everyone who took the metaphorical surfboard and threw themselves into this wave has done so by fully investing their creativity and humanness into it and as result amplifying their creativity. We are seeing right now a Cambrian explosion of new tools and apps, new research, discussions and think pieces, new forms of storytelling, pictoral and animated art as well as games. And a lot of that by people who didn’t have the means or craft to express their creative vision before. We see people who can’t code programming apps and games. People who can’t draw or paint creating graphic novels or design fashion or houses. People who can’t animate make videos and people who can’t sing or play an instrument write and produce new songs. People haven’t produced creative outputs in the past because it was a chore, but because they wanted to express themselves. I don’t see why that inherent drive of humans to express themselves and their ideas would go away with new tech (it didn’t happen with the printing press, photography, radio, TV or the web – despite similar forecasts by critics at the time). Rather the opposite: AI, like every tech before, will amplify our capabilities to express ourselves and open up new avenues and techniques to do so.

Do you want to explore these and other questions regarding Generative AI with your organization or your team? Then reach out at IntegralKM@gmail.com and we can tailor a session to your needs, supported with hands-on examples on how to use ChatGPT and similar tools in your everyday work!

Artificial Intelligence For Everyone Has Arrived! What Does That Mean For Knowledge Management?

noreply@blogger.com (Stepping Higher - Reflections on the Knowledge Age) — Fri, 09 Dec 2022 19:19:00 +0000

Anyone who has been following the discussions in Internet tech forums this week gets the unmistakable feeling that we are currently experiencing a qualitative transition, from a yesterday in which artificial intelligence (AI) was either a thing of the future or worked in secret behind specialized systems (Google Auto-Complete or error-prone Tesla Autopilots), and a today in which the technology is suddenly available to all Internet users at the push of a button for a wide variety of tasks and queries. Change happens, as Hemingway put it, "first gradually, then suddenly." We are experiencing just such a sudden moment.

But why am I writing this here in a knowledge management column? Let's first take a step back: What is knowledge management fundamentally about? Knowledge should be collected, managed and used within an organization. And users within this organization should be able to access relevant knowledge and information quickly and easily. All with the goal of facilitating the work of employees, making better decisions, and ultimately increasing the effectiveness and efficiency of the organization.

Up to now, organizations have used various tools and methods for this purpose, such as databases, document management systems, knowledge portals or corporate social networks. These help us to store and organize information and to share it with users in various forms.

A turning point for AI in everyday life

And now comes ChatGPT - an AI system that specializes in machine learning in speech processing. Such AI systems can analyze massive amounts of unstructured text, extract important information, and then present it back to users. This helps in finding relevant information and documents as well as in decision making. With the release of the ChatGPT chatbot last week, such systems are no longer open only to financially strong companies, but theoretically to any Internet user. The underlying system GPT-3 is not new, yet the intuitive user interface as a chatbot is.

But what exactly does this mean for everyday work in our organizations, today and going forward? How could AI be used in knowledge management in concrete terms, and what are the benefits, opportunities and risks? This whole week I’ve been testing ChatGPT and thinking about the possible implications for our work.

What is clear is that this is a real technological breakthrough (that I personally have been waiting for for a while) that unleashes a whole avalanche of ethical, political, and philosophical questions that we can't cover all in one post here (more on that hopefully in another post later).

But if we first focus very specifically on what the availability of such AI means for knowledge management in organizations like ours, I would say that the following scenarios are foreseeable (or have already occurred in some cases):

1. Support in finding relevant information and documents

Imagine you're looking for a specific document, but you don't know exactly where to find it. With an AI-based chatbot fed with your organization's complete database, you could ask your question in the chat, and the system would then automatically track down the relevant documents and information from the company's various systems and provide them to you. It's like having your own personal assistant researching the information you need. Or a hundred of them.

2. Automated generation of reports and analyses

AI systems can analyze large volumes of unstructured data and extract important information and knowledge. From this information, AI then automatically generates reports, analyses, or presentations that are useful for communication or decision-making within the organization. For example, an AI system could automatically identify trends and patterns in an NGOs donations and visualize them in a report. Or it could analyze field reports from projects, identifying recurring problems and challenges that arise in different contexts, and then formulate "lessons learned" from them.

3. Automation of simple knowledge work

AI systems like ChatGPT can also help automate certain tasks and processes within the organization. For example, it can generate a list of ideas on a topic, summarize meeting minutes, formulate first drafts of letters, press releases, or talking points, compile an FAQ from a given text, or draft the outline of a social media campaign on a topic (including Facebook posts, tweets, and hashtags). And this isn't stuff of the future, we've already tried all of this out this week.

4. Finding the right contacts

An AI system that can access an organization's database could help users find the right colleagues at the right time who can help them with certain topics and problems. Based on user queries and profiles, the system could learn which colleagues are particularly competent in which areas and what experience they have in relation to certain topics. If a user then asks a question about a certain topic, the chatbot would suggest appropriate colleagues who can help them with their problem.

What is striking when using ChatGPT for the first time is that the special strength of the chatbot lies less (or not only) in the quick retrieval of facts, but in the quite astonishing ability to independently create content. One could speak of a Copernican Revolution of creativity: A paradigm shift by which, for the first time, humans are no longer the only (and, in the long run, perhaps not the primary) source of creative content. What this means for the flood of information on the web, the value of people's professional expertise, for art and the creative industry, or for democratic discourse in society, we cannot yet even foresee. But the consequences will be very far-reaching.

World knowledge or organizational knowledge?

Basically, we have to distinguish between external AI systems like ChatGPT, which have been trained by vendors (in this case the company Open AI) with the available world knowledge (which should not be relied upon to reproduce correctly by the way), and internal systems, which are entrusted with the data stock of one's own organization (where many questions regarding privacy, hosting, security, etc. would have to be clarified).

The former case is a reality as of this week with ChatGPT. Give the bot a task via chat and it does it in seconds with the quality of a high school graduate, albeit (still) a bit template-like and soulless.

The second case is not yet a general reality (or not yet in the affordable range), but I am sure that in the near future various providers will come up with commercial offers for organizations of various sizes. And even then, it won't be overnight, because training an AI with your own data takes quite some upfront work. The opportunity here, however, is that as training and internal data grows, an organization builds its own internal AI instance that exactly matches its needs, history, operations, and intent, which is invaluable in the long run. Because it will be the output of these proprietary AI memories that will give organizations a long-term competitive advantage in the marketplace of ideas. But of course, the reverse is also true: Organizations that close their minds to this development now, thinking that all of this has nothing to do with them, will have a hard time surviving in the long run. First gradually, then suddenly.

Going Back to Dave Snowden’s Seven KM Principles

noreply@blogger.com (Stepping Higher - Reflections on the Knowledge Age) — Thu, 18 Aug 2022 12:21:00 +0000

In June this year I attended the International Conference on Knowledge Management (ICKM) 2022 which conveniently took place in Potsdam, right around the corner of my current home base Berlin. One of the highlights was the key note speech of David Snowden. David is of course always a treat to listen to, but in his speech intro, he once again summarized so succinctly some of the key aspects of what KM is all about, that I wanted to re-state them for myself. So here are his gold nuggets:

1. Knowledge can only be volunteered, it cannot be conscripted

The sharing of knowledge is inherently a human behavior. Yet it only happens when we are intrinsically invested in the positive impact that the sharing of our knowledge has on the receiving end (because we want to help, because we get nice feedback, because we want to build relationship, because it might help ourselves in the future, etc.). If we are told by someone else that we must share a particular knowledge, there is automatically a loss of quality, because we have no actual stake in the outcome of the knowledge sharing process. So the piece of knowledge that is shared is of lower quality, which inevitably leads to lower adoption and ultimately to lower impact (or no impact at all). This is maybe the most important KM principle of all, yet organizations unfortunately ignore it all the time when they create mandatory knowledge transfer processes, databases of lessons learned or force individuals into regulated knowledge exchange formats and groups. Instead, we must work with the intrinsic motivation of people to be of help to others, to achieve impact, to get acknowledged as experts, get elevated in their status or be rewarded for the good work they do.

2. We only know what we know when we need to know it.

The effort to document every bit of knowledge in advance is a huge waste of resources. The reason is that it is impossible to know ahead of time which parts of all our potential knowledge will be actually useful to someone else in a specific situation. “With high abstraction and high codification, you get rapid diffusion, yet the knowledge remains superficial. With low abstraction and low codification, diffusion becomes difficult, but the knowledge is actually denser.” And whether we can afford to go the path of low abstraction depends on the context one is in. In a specialized group with experts in a topic, another expert can convey more deep knowledge in 2 min than what he could communicate in 6 min to a laymen’s group, because there is a common reference based and a common knowledge around the topic. That’s why silos exist in the first place. Because it is more economic (in terms of effort) to focus on knowledge transfer just within silos. One way then to handle knowledge transfer across silos then is either through metatdata (so people can find things without having to know the professional lingo). The other way is to foster the emergence of informal communities, which leads us to the next principle.

3. In the context of real need few people will withhold their knowledge.

Which is why we have to be careful in formalizing and putting mandatory elements around communities. We don’t create healthy communities by building formal constructs in which networking must happen in this or that way. We must stimulate the formation of informal communities, and those informal communities which stabilize we then re-enforce so they can thrive. So we shouldn’t create a predefined set of Community of Practice from scratch, because the energy cost to do so is massive. We instead stimulate the environment to see what gets traction and then we enforce and put boundaries in place and invest more energy in to it in order give them the institutional support they need.

4. Everything is fragmented.

One of the reasons social media works is because it is fragmented. People like to share anecdotes and snippets. “The human brain evolved to handle fragments and put them together, not to process structured information.” This is how we humans share knowledge, at the fire place, at the dinner table, at the coffee machine. And “a cluster of such anecdotes is more valuable than a structured document”. We must keep this in mind when we encounter tendencies to overly rely on explicit knowledge encoded in formal documents. Formal documents, while not without merit in specific situations, are not what is best suited to diffuse knowledge. We think and communicate primarily in fragmented anecdotes and snippets, so we need to foster environments where such knowledge fragments can live and promulgate.

5. Tolerated failure imprints learning better than success.

“All the stories we tell children as learning stories around the world are stories of failure, not success.” It’s never ‘Hansel and Gretel had a plan, went into the woods and know how to get out of it.’ No, its ‘Hansel and Gretel got lost in the woods and imprisoned by the witch, and had to learn on the fly how to rectify their mistake.’ The human brain picks up failure faster than success, because avoidance of failure is a more successful strategy than the imitation of success. We should build worst practices, not best practices (which might include fictional stories as well as real-life stories). The principle of loss aversion popularized by David Kahneman shows us that humans are biased to value the avoidance of pain multiple times higher than the prospect of gain. We have to work with that bias in KM as well.

6. The way we know things is rarely the same as the way we report we know things

We should capture learning as the learning happens, because a few hours later, we remember the learning already differently. “If we do a project retrospective, people who fail in a project will remember the past completely differently than people who succeed in a project. We adjust our memory to conform with the reality of the present”. That is important to know, because so much in KM relies on retroactive reporting, which is almost certainly wrong and will not repeat itself in the same way. The answer to this is again the fostering of informal communities, in which experiences can be talked about and are reflected upon in real-time.

7. We always know more than we can say, and we can always say more than we can write down.

There is always a great loss of content and a loss of context when transferring knowledge. It is much easier to capture a narrative and re-use a narrative e.g. in a best practice document than to improvise solutions when the situation and context changes. That doesn’t mean that best (or good) practice documents can’t be helpful in certain situations. But we must not delude ourselves into thinking this is the essence of knowledge. The essence most likely got lost along the way, and we need to find complementary formats and channels through which the essence of our experiences is shared. This is again a warning of the overreliance on encoded knowledge in documents.

I always find it helpful to re-phrase and document (ha, the irony!) such pointers for me once in a while, so I can go back to them again and again to remind myself of what not to lose sight of. No matter where we are in our professional journey, it is always useful to hone the basics, lest we get overconfident and complacent. I hope it is helpful to you too.

What Is Integral Knowledge Management And Why Do We Need It?

noreply@blogger.com (Stepping Higher - Reflections on the Knowledge Age) — Fri, 05 Aug 2022 10:27:00 +0000

Why do organizations struggle to consistently achieve results in knowledge management (KM)? Every employee in an organization can testify to the various pain points that KM is supposed to address in organizations, and they usually acknowledge the helpfulness of some individual tools and methods, but almost all organizations struggle to put them into a coherent conceptual framework that explains when and why KM as a whole succeeds in an organization, and when and why it doesn’t. I suspect that one of the key reasons for this might be the failure to adapt the type of KM approach to the values and work conditions of the organizations it is applied in, as well as the values and life conditions of the workers that are the target of the KM initiatives.

Whenever we ask someone in an organization what KM is really about, we get invariably different responses. Some will emphasize the structured organization of existing documents and information, the next one will highlight mandatory business processes, some others will talk about learning and innovation, while yet others propose it is all about free-flowing exchange among people and networks. Why this difference in responses? Because different people will have a different perception of what “knowledge” itself means to them, and therefore what ways are best suited to deal with it (aka “manage it”). The truth of course is that they are all partially right. But because people will answer the overarching question “what does knowledge mean to you” based on their own value set and where they are in their life in general, they will focus mostly on those aspects that speaks to their specific needs, values and particular worldview.

KM at different stages of socio-psychological development

This is where evolutionary models of socio-psychological development, specifically Integral Theory and Spiral Dynamics, come in. By applying their model of stages of human development to the business discipline of Knowledge Management, Integral Knowledge Management (Integral KM) fills this gap and shows under which circumstances specific KM elements, tools and methods can add value (and where they might not). This enables organizations to understand their knowledge workers better, avoid costly mistakes in the implementation of KM initiatives and instead assemble a portfolio of KM interventions that are suited to the environment they are applied in and the people that are supposed to apply them.

But what does ‘integral’ mean, and what makes something integral in this context? The term ‘integral’ refers to a specific worldview in the Spiral Dynamics (SD) model (developed by Don Beck, Chris Cowan and Ken Wilber based on the work of Clare Graves). For the sake of this post, we will look at six different worldviews that the Spiral Dynamics model distinguishes. (There are two more, namely one before the magic worldview, and one after the integral worldview, but they don’t add much to the purpose of this specific discussion about knowledge management). Each worldview was assigned a color by Beck and Cowan, which have no specific meaning other than to make it easier to refer to them:

The magic worldview (PURPLE) seeks to protect itself from a world that is filled with magic and forces outside of its control.
The hero worldview (RED) thinks primarily in win/lose power relations
The absolutistic worldview (BLUE) champions collective rules and absolute truth
The modern worldview (ORANGE) pursues rational science, competition and personal success
The post-modern worldview (GREEN) values community, global diversity and inclusion
The integral worldview (YELLOW) values adaptation and tries to integrate the strengths from each of these other worldviews into an overarching systemic whole.

The term “integral” thus refers to this last worldview that looks at various historic ways of seeing the world as each holding an important piece of the puzzle without being sufficient on their own. To learn more about what the Spiral Dynamics model is about, this website is a good start.

So lets go through the difference worldviews (also called vMemes or value systems in SD language) and spell out what role knowledge plays and how knowledge management as a discipline works in each of them.

PURPLE – The magic organization

In the PURPLE worldview knowledge provides identity and belonging. Knowledge comes from the elders and is handed down from generation to generation in the forms of stories, rituals and practices. The ancestors are revered for their mystical powers and wisdom, and the goal is to protect this knowledge (and the rites and practices by which it is preserved) in order to ensure the safety of the social unit. Outside forces are not rationally understood, and therefore threatening, so attempts are made to establish control and a sense of safety through rituals and symbols that convey protection and meaning. Practical experiential knowledge about the ecology of one’s surroundings is intertwined with mystical beliefs and practices, superstition and pre-institutional religion. The knowledge organization is looked at like a family that holds unique generational knowledge which protects it from the outside world.

While this stage of development is most dominant in indigenous societies, we can observe some of its characteristics within our modern societal structures and organizations as well. And if an organization has employees with a strong PURPLE value set, it must cater to their needs in order to mobilize them for knowledge management.

So how can we mobilize coworkers with their gravitational center in this worldview? We can celebrate and reaffirm the principles of the organizational founders, and derive action and policies from experiential history. Affirm the value of indigenous ecological knowledge and use it to guide practical applications that provide value to the organization today. Strengthen a family-like culture among coworkers, where seasons, milestone and rites of passage are consciously and regularly celebrated, and use songs, images and physical items as symbols of organizational knowledge, identity and purpose (sports clubs for example do this very well). Coworkers with their gravitational center in PURPLE are predestined to serve as the elders, advisors or “shamans” of the organization, holding historical knowledge and wisdom that will prove to be of value to the generation making the decisions.

Typical KM initiatives for PURPLE organizations are biographies, organizational histories and corporate museums, as well as any kind of storytelling that conveys meaning and wisdom, supported by practical rituals, practices and symbols that help anchor the experiential knowledge and insights.

While stories, rituals and the reverence of founders can create a sense of identity and community, they will only get us that far in terms of dealing with practical knowledge challenges in today’s organizations. The flipside of a PURPLE worldview is isolationism, aversion to outside knowledge, people and change of any sort, and a tendency to reject today’s reality in favor of a frozen-in-time image of history.

RED – The hero organization

The key knowledge principle for this worldview is knowledge is power, wherein the world is predominantly seen as a power struggle that knows only winners and losers. Knowledge in this context becomes an instrument to increase one’s sphere of influence and secure one’s position vis-à-vis others. The goal is informational superiority over others in order to achieve the objectives of the in-group and to prevent the out-group from succeeding. Active disinformation and the destruction of existing knowledge or prevention of new knowledge are viable tools in order to dominate opponents. Hero figures with informational superiority or insight venture out to act on their inside knowledge to advance their interests and save themselves and their in-group from defeat. The knowledge organization is looked at like a battleship that uses knowledge to assert its dominance and influence, and the knowledge workers in this image become warriors.

How to mobilize coworkers with their gravitational center in this meme: Emphasize the interest of the organization (in-group) versus the organization’s competition (out-group), and frame KM tools as weapons to be wielded skillfully in order to advance the interests of the tribe. Let ‘heros’ in your organization venture out to discover new knowledge that can strengthen the position of the tribe vis-à-vis others. When RED coworkers have good communication skills, their aptitude for manipulation allows them to extract information where others fail, which can make them excellent investigative journalists or detectives.

Typical KM activities at this level are secretive, closed-door meetings, ideally without any written records (they could be used against you), clandestine information gathering, withholding information as well as whistleblower protocols and source protection.

The downsides to this approach to managing knowledge, however, should be obvious. Knowledge is not shared to the extent it could be as the audience that is “in the know” is very small, learning is very limited and distrust and secrecy tends to prevent productive collaboration and innovation.

BLUE – The absolutistic organization

Within the BLUE worldview is knowledge is order and truth. Orderly structured knowledge allows us to do the things that are right and true. The goal is to teach and affirm what is already known as the right knowledge and disseminate it to those who don’t have it so they may benefit. Knowledge is protected by authoritative gatekeepers and knowledge sharing happens on a need-to-know basis via clearly defined hierarchies and channels. New knowledge that contradicts the group’s ‘right’ knowledge will be passively resisted, purposefully hidden or actively opposed. Long-established knowledge, security of information and confidentiality trumps open knowledge sharing, freedom of thought and innovation. Explicit knowledge in documents and the collection and organization of it, as well as its dissemination via “proper” channels is heavily emphasized over tacit knowledge and unstructured exchange. The knowledge organization is viewed as a bureaucratic institution of doctrine with its history and rulebook as its bible that should be adhered to without deviation.

How to mobilize coworkers with their gravitational center in this meme: Cater to their need of security and structure by establishing a set of explicit rules and guidelines for knowledge documentation and exchange. Put them in charge of necessary archiving tasks, templates or needed taxonomies while keeping the regulatory burden to a minimum. Use them for KM initiatives that require executing top-down instructions and compliance, e.g. documentation for auditing purposes. For the purposes of KM, BLUE coworkers’ sense of order, hierarchies and adherence to rules and processes make them excellent archivists, librarians, evaluators and compliance monitors.

Typical KM initiatives that appear in BLUE organizations are document management systems and taxonomies, centralized lists and databases, editorialized knowledge repositories, archives, libraries, as well as any kind of formal templates and processes that ensure compliance with top-down rules and procedures.

While the absolutistic approach to KM can cover a lot of ground in terms of archiving structures and necessary guidelines and prescriptions, it is not well equipped to facilitate new ideas, innovation or open exchange and discussion with different audiences. Which is where people with modern and post-modern mindsets come in.

ORANGE – The modern organization

The key knowledge principle here is that new knowledge is the key to success. Within the ORANGE worldview, knowledge is empowering individuals and organizations to discover what is not yet known and to explain what is not yet understood, so they can learn, grow and gain a competitive advantage in the marketplace of ideas. Scientific knowledge discovery and technological progress are the key tools, and increased efficiency, effectiveness and performance are the end goal. Proven experiential knowledge as well as academic credentials convey status, which elevates the position of individuals in their social context. The knowledge organization is viewed as a machine that has knowledge as an input and organizational results as an output, with the knowledge worker taking the role of an engineer or assembly-line worker who has to make sure that knowledge is converted into results.

Coworkers with their gravitational center in this worldview are motivated by status and success. To mobilize them, demonstrate how specific knowledge management activities gives them as individuals as well as their organizations a competitive edge. Tie knowledge objectives to their performance scorecard and link KM activities to the strategic objectives of the organization. Provide learning opportunities for professional development and give them channels and platforms through which they can demonstrate their knowledge and promote their status as experts in their fields. Due to their drive for discovery and progress, ORANGE coworkers can be excellent innovators in organizations, as well as, intrapreneurs, technologists and researchers.

Typical KM initiatives driven by ORANGE coworkers are innovation and research efforts, learning initiatives (often in the format of one-to-many), publications that convey latest state-of-the-art knowledge, as well as any kind of technology-driven solution where technological innovation takes center stage, from data warehouse systems, office applications and web content solutions to communication systems, social collaboration tools and artificial intelligence.

However, the focus on achievement, performance and status within the ORANGE worldview also has its downsides. When everything is about goals, numbers and money, what is often lost is the one resource where knowledge comes from in the first place: The people of the organization. Which is why the next worldview has an explicit people focus.

GREEN – The post-modern organization

For the GREEN worldview the key knowledge principle is that all knowledge is valuable and should be shared as widely as possible. In the GREEN worldview, humans and their knowledge needs take center stage and the focus turns to implicit knowledge emerging though conversation, connection and collaboration. Knowledge management is no longer conceptualized as an engineered machine with inputs and outputs, but as a network where everyone engages with everyone, and which should be expanded to include ever more people. Knowledge workers are understood as networkers, facilitators and service workers. Everyone has something to share, and everyone’s knowledge is of equal value, and the best results are achieved through inclusive and diverse collaboration. There are no absolute truths anymore, and the paradigm of knowledge competition is replaced with the paradigm of open knowledge equity. Knowledge workers are trusted to identify knowledge relevant to them via decentralized and self-organized processes and exchanges, while overly rigid structures, processes and templates are rejected.

Coworkers with their gravitational center in this worldview are intrinsically motivated to connect with others, share knowledge and collaborate. For them to function most effectively, they must be given a social networking environment, equipped with digital collaboration tools. Communities of Practice and online knowledge networks, open space workshops as well as social media and corporate social networks are expressions of the style and preferences of GREEN knowledge workers. GREEN coworkers make fantastic workshop facilitators, online community moderators and social media strategists. Learning opportunities for GREEN coworkers must be participatory and value the contributions of all present.

The downsides of a KM approach that heavily emphasizes the GREEN meme can be lack of clear structures and guidelines when they are needed. Free flowing and unstructured knowledge exchange, while being a boon in to innovation and the creation of new opportunities, can become chaotic, make search for explicit materials difficult and tie up colleagues in endless discussions and get-togethers without clear outcomes. Knowledge discovery becomes are function of active networking and social interactions, which disadvantages introvert coworkers who diligently work away in their cubicles, but don’t like to put themselves out there. Most of all, because all opinions are important and hierarchies are rejected, GREEN organizations have a hard time making tough executive decisions when needed.

YELLOW – The integral organization

For the integral worldview Knowledge is complex, multi-faceted and always changing. Integral, aka YELLOW thinking understands that all the previously expressed views of knowledge and knowledge management are, to use Ken Wilbers words, “true but partial”. The goal therefore is to discern which methods, tools and practices are helpful in any particular context, and which are not, use only those that add value in a given situation, and integrate the various elements into something that is bigger than the sum of its parts (hence the term “integral”). The YELLOW worldview looks at the knowledge organization as a system in which all the previous worldviews, mechanisms and experiences are present, interconnected and mutually influencing each other, and which itself is embedded in again larger systems of the economic, political or social sphere that it needs to navigate. Knowledge is understood as always incomplete, always fluid, always changing. However, unlike the GREEN meme, YELLOW acknowledges that not all knowledge is equal, that knowledge hierarchies do exist and have real world consequences. The organization in this worldview is neither a family, warring tribe, or a bureaucracy, nor a high-achieving machine or a diverse network. Instead, it is seen as a living organism that integrates all those images, always adapts to changing circumstances and pragmatically and flexibly does whatever it needs to in order to succeed in a particular situation. It does so by activating specific strengths of the organization as family, war tribe, bureaucracy, machine or network, whenever helpful.

Coworkers with their gravitational center in YELLOW usually do not need to be explicitly mobilized for knowledge exchange. They naturally seek out information and knowledge from different parts of the system and actively seek to disseminate it throughout the system, all while pushing for a non-ideological, integrated approach that acknowledges the different contributions and the value-add from all other modes of KM. YELLOW coworkers can speak the language of colleagues at all previous memes and are suited to mobilize them by playing to their distinctive preferences and skills. They therefore can serve the organization well as strategists, advisors, trainers and cross-organizational diplomats.

Typical KM initiatives driven by YELLOW coworkers will often apply agile development techniques, systems thinking and systemic design, complexity science (e.g. the Cynefin framework), collective intelligence and sensemaking approaches, and will work on the development of knowledge strategies, trainings, advocacy campaigns and organizational transformation projects that integrate various different elements from different development stages as needed.

Towards an integral knowledge management approach

Of course, the above is a gross oversimplification of both the SD model and the realities of KM in our organizations. Every model is wrong, but some are useful, as the adage goes. And of course, no snigle organization is exclusively grounded in just one specific worldview. In reality, all worldviews are present in every organization (and in fact every individual), and there is maybe a center of gravity around which the organizational culture revolves. However, I believe applying the frame of this development model to KM gives us a new perspective of how to think about our corporate KM strategies and practices, and can give us a viable path forward where the discipline previously has always been stuck:

1. It explains the frictions between different people within an organization who have vastly different ideas of what KM should focus on (e.g. BLUE’s focus on explicit knowledge and closed mandatory processes vs. GREEN’s focus on implicit knowledge and open exchanges)

2. It acknowledges that none of the opinions voiced about KM in an organization are fully right or wrong, but that each of them holds partial truth and has validity within the context of the person who is expressing them. The real harm instead comes from claiming exclusivity for one’s own view, ignoring the downsides of pursing a path exclusively based on one worldview (and therefore view of KM), at the expense of ignoring the strengths of all other worldviews.

3. It maps out a way how the different needs and values present in an organization can be catered to at the same time, by avoiding a “one-size-fits-all” strategic approach to KM and instead utilizing the strengths of different worldviews in situations where they are helpful, while unideologically setting aside those elements that do not add value in a particular situation.

Most of all, however, practicing integral KM allows us to become conciliators in a world increasingly dominated by hardened ideological battle lines and polarized opinions. It allows us to accept that every knowledge worker has a right to be where they are, and to have the needs and values they have. Our job is not to judge or to play one opinion or approach against the other, but to mitigate worldview expressions that are harmful to our groups, organizations and the world, and to integrate those elements that are healthy, useful and beneficial for all of us. This of course goes much farther than the discipline of KM, but if KM can contribute even a small part to this mission, I will be very proud to be part of the KM profession.

Why Bitcoin is Integral Money

noreply@blogger.com (Stepping Higher - Reflections on the Knowledge Age) — Tue, 19 Oct 2021 09:13:00 +0000

By Johannes Schunter

What makes something integral? The term ‘integral’ refers to a worldview in the Spiral Dynamics (SD) model (developed by Don Beck, Chris Cowan and Ken Wilber based on the work of Clare Graves) that looks at various historic ways of seeing the world as each holding an important piece of the puzzle without being sufficient on their own. The hero worldview thinks primarily in heroic win/lose power relations, the absolutistic worldview champions collective rules and absolute truth, the modern worldview pursues rational science, competition and personal success, and the post-modern worldview values community, global diversity and inclusion. An integral mindset then tries to integrate the strengths from each of these worldviews into an overarching and balanced whole. To learn more about what the Spiral Dynamics model is about, this website is a good start.

In the following, I argue that as far as monetary technologies, financial assets or currencies are concerned, Bitcoin is the closest thing to integral money that we currently have, which should have implications on how the integral community deals with it.

What is Bitcoin?

Here is a primer from the Bitcoin.com website:

“Bitcoin is the first and most widely recognized cryptocurrency. It enables peer-to-peer exchange of value in the digital realm through the use of a decentralized protocol, cryptography, and a mechanism to achieve global consensus on the state of a periodically updated public transaction ledger called a 'blockchain.'

Practically speaking, Bitcoin is a form of digital money that (1) exists independently of any government, state, or financial institution, (2) can be transferred globally without the need for a centralized intermediary, and (3) has a known monetary policy that arguably cannot be altered.

At a deeper level, Bitcoin can be described as a political, philosophical, and economic system. This is thanks to the combination of the technical features it integrates, the wide array of participants and stakeholders it involves, and the process for making changes to the protocol.

Bitcoin can refer to the Bitcoin software protocol as well as to the monetary unit, which goes by the ticker symbol BTC.

Launched anonymously in January 2009 to a niche group of technologists, Bitcoin is now a globally traded financial asset with daily settled volume measured in the tens of billions of dollars. Although its regulatory status varies by region and continues to evolve, Bitcoin is most commonly regulated as either a currency or a commodity, and is legal to use (with varying levels of restrictions) in all major economies. In June 2021, El Salvador became the first country to mandate Bitcoin as legal tender.”

So what makes Bitcoin integral? It features multiple essential elements that are anchored in different worldviews of the SD spiral, which integrated together make it something new that is more than the sum if its parts, and thus, integral:

The hero worldview (marked by the SD model with the color RED)

Bitcoin was designed in 2009 (see original white paper here) in explicit response to the Great Financial Crisis and its handling by governments which was read by many as an institutional betrayal of global taxpayers. It thus represented an anti-establishment counter-movement that promoted sovereignty of the individual who – with Bitcoin – would not be at the mercy of non-trustworthy governments and financial institutions anymore, but could save, transact and operate as their own bank free of censorship, exploitation, surveillance or confiscation (either directly or via inflation).

Another defining aspect is the fact that Bitcoin was created by the anonymous individual or group ‘Satoshi Nakamoto’ which resulted in a vibrant hero myth within the Bitcoin community, who speak the name in reverence, ponder on his/their true identity and never cease to be amazed by the foresight, elegance and robustness of their technological invention (solving among others the Byzantine General’s problem, a long-standing math problem in computer science).

Both of these elements are strongly RED features (aka rooted in the hero worldview), and they make up an important piece of what Bitcoin is.

The absolutistic worldview (BLUE)

Bitcoin also features a zealous, quasi-religious ‘Maximalist’ community of Bitcoin holders who commit to never sell their Bitcoin and believe without a doubt that Bitcoin will replace the US Dollar as the world’s next reserve currency (a notion championed among others by the 2018 bestseller “The Bitcoin Standard”) due to its pre-programmed halving cycle (the amount of Bitcoins that can be brought into existence is cut by half every four years), its absolute scarcity (only 21 million Bitcoins in total can ever be brought into existence), its final and irreversible settlement of transactions, and its iron-clad rules-based governance mechanism that achieves consensus over new transactions on the blockchain and improvements to the software. ‘Code is law’ is the philosophy behind it, and it illustrates the absolutistic BLUE qualities of this new monetary asset that unlike any other asset in history cannot be stolen via corruption, confiscation, inflation or increase of the money supply by governments and thus protects the asset holder from the whims and moods of power players. In Satoshi’s own words:

“The root problem with conventional currency is all the trust that's required to make it work. The central bank must be trusted not to debase the currency, but the history of fiat currencies is full of breaches of that trust." (Bitcoin White Paper 2008)

The bitcoin consensus algorithm solves this problem of trust, and provides an ultimate unbreakable blue ruleset to prevent exploitation of monetary assets or transactions by non-trustworthy actors.

Or as Preston Pysh, host of a popular business podcast, put it:

“Everybody in the global economy is cheating. Bitcoin forces all players of the game to now have to play by the rules” (https://twitter.com/PrestonPysh/status/1446637368086302723)

The modern worldview (ORANGE)

The most prominent element of Bitcoin for many people is its price, specifically its astonishing price rise over just a few years. Since it first started trading in July 2010 at a price of USD $0.05 per Bitcoin, Bitcoin has reached a value of above $60,000 per coin as of Oct 2021, which represents a unfathomable return of 123 million(!) percent or a 347% return per year. No other asset can compete, and over the last decade Bitcoin has beaten all asset classes (stocks, bonds, real estate, precious metals, commodities) by orders of magnitude, creating countless new millionaires and a number of new billionaires in the process. It is this aspect that also draws the scrutiny of uninvested observers who conclude this can only be explained by fraud (read here Lyn Alden's explanation why the critique of Bitcoin as a Ponzi scheme is flawed), and will inevitably result in a giant crash that will collapse Bitcoin to zero (read here about the 432 times Bitcoin has been declared death by the media since 2010). The truth is that only very few who bought in the early years held on to their Bitcoin, and those who did and after a long run cashed out for a profit (or are still holding as we speak) were rewarded for their exorbitant risk with exorbitant rewards. Bitcoin is the ultimate capitalist ORANGE asset which encourages individual risk-taking for possible outsized reward like no other investment before. Which other entrepreneurial or technology venture could give you a perspective of 1,000-fold, 10,000-fold or million-fold returns over the course of less than a decade?

Of course, Bitcoin also has been at the cutting edge of science and technology with its groundbreaking cryptographic innovation, grounded in math and cold rationality and thus in an modern ORANGE mindset.

The post-modern worldview (GREEN)

Maybe the most surprising aspects of Bitcoin to the uninitiated are its qualities that are based in the values and mechanisms of the post-modern worldview. Bitcoin is not just a cold capitalist asset, it is also a digital decentralized peer-to-peer payment network with no single point of failure, and a strong egalitarian and anti-institutional community behind it, that brings with it all the hallmarks of large social networks (viral adoption, exponential growth, failure redundancy and resilience to recover from shocks). Because of these qualities, Bitcoin has over the years become a life raft for millions of people who are (unlike the financially privileged citizens of OECD countries) living under conditions of financial oppression with double-digit inflation rates, violation of property rights by state actors, censorship and strict capital controls. Alex Gladstein from the Human Rights Foundation has collected countless stories from countries as disparate as Cuba, El Salvador, Venezuela, Senegal, Palestine, Turkey, Afghanistan, Hong Kong or Myanmar who were able to send money to relatives, receive donations for their activism, take their assets with them when fleeing from war or persecution or simply save their nest egg from rampant government-induced inflation. The “Lightning Protocol” which acts as a payment layer on top of Bitcoin’s settlement layer has recently enabled instant, quasi-free and permissionless transactions of even the smallest amounts across borders, and in the process solved the problem of international remittances and their high fees almost overnight. The profound real-world impact for the millions suffering from financial oppression leads Gladstein to the conclusion that

“Satoshi was a human rights activist igniting the biggest and most effective peaceful protest of all time, planting a seed of liberty at the root of exploitation and tyranny with nothing more than free and open source code.” (https://twitter.com/gladstein/status/1449233180955795458)

If unintentional or by design, the incentives created by Bitcoin’s RED, BLUE and ORANGE qualities align in ways that make it a tremendously powerful tool against oppression and disenfranchisement of the poor and disadvantaged, which are hallmark values of the GREEN worldview. For more information on this dynamic, this article is a good start.

Even the popular criticism of Bitcoin consuming too much energy and thus contributing to climate change has recently been turned into its opposite by the realization that Bitcoin’s incentives, which naturally seeks out cheap and renewable or standard sources such as hydropower or flared natural gas make it the perfect tool to help balance out the unpredictable load of a renewable power grid. Going forward, this will make Bitcoin likely a driver for adoption of renewables, rather than an accelerator of climate change.

Bitcoin as Integral Money (YELLOW)

None of these individual qualities above can on their own deliver the benefits that Bitcoin as a monetary asset and a payment network offers today. Nor could any of the worldviews above on their own have given birth to such a dynamic that marries the benefits of all of them so neatly, creating synergies in the process that make it bigger than the sum of its parts. In the past, each worldview brought with it its own monetary standard: commodities for RED, gold/silver currency for BLUE, gold-backed paper money for ORANGE and untethered fiat money for GREEN. An integral, aka YELLOW approach to money will integrate the qualities of all of them, yet transcend them in new ways, initiating a new era of how currency and economics work and replacing the GREEN fiat money paradigm in its current form. An integral society and economy will not be a paradise, and it will eventually be transcended by something new again. So integral money will not be the end all to solve all problems, it will in fact even create entirely new ones. But integral money will emerge. Bitcoin is the first candidate on the horizon that can realistically vie for this role. That doesn’t mean it is guaranteed to succeed. However, given the fact that due to network effects an incumbent active network is difficult to be replace by a new player after a certain threshold is reached, every day that passes by without Bitcoin going away, it increases the likelihood that Bitcoin maximalists may eventually be proven right and Bitcoin will be an important part of an integral future.

Author's note: I admit I don't have all the answers and might be partially or completely wrong. I welcome any constructive criticism of this view. In particular, I would be interested in what aspects of Bitcoin may contradict its classification as integral money, what additional qualities integral money should have in your view, and which monetary asset or technology in the current financial landscape could play such a role in the future.

Spiral Dynamics: A Model for how our Understanding of the World is Changing

noreply@blogger.com (Stepping Higher - Reflections on the Knowledge Age) — Mon, 21 Sep 2020 08:46:00 +0000

COVID gave me a lot of extra time to think, and in the spirit of the title of this blog, I wanted to share some reflections about human knowledge that I am carrying within me for a while now.

We all noticed how polarized our discussions on social media and offline have become, and they often crystallize along a right/left spectrum. To the majority in my circle of friends, the main threat to humankind consists of the destruction of its environment (pollution, climate change, biodiversity, etc.) and growing inequality and exclusion in all its forms (poverty, racism, sexism, etc.). To a smaller part of my personal circle of friends (but to many outside of it), socialism/communism and the suppression of free enterprise and individual liberties seem the primary threats of our time. The COVID pandemic brought this chasm to the forefront like even Brexit and the Trump election couldn’t.

I would like to suggest a different frame about thinking and talking about these things (because clearly no one in either group is convinced by any arguments of the other group). It is not my own frame, but a sociological (and to some extent spiritual) model for the evolutionary development of individuals, organizations, and societies, based on the work of Clare Graves, Don Beck and Ken Wilber (which are all Westerners, giving the model a somewhat Western tilt, for which I apologize in advance). The model is called Spiral Dynamics and posits the following:

Like human development of individuals who go through different levels of consciousness as they move from infant to toddler to child to teenager to adolescents to adults to middle-agers to old age, human societies as a whole similarly go through such stages of consciousness (awareness and views of the world and themselves in it). Each stage is important for society’s development, none of them can be skipped (like you can’t skip those sucky teenage years), and each open up a new world of understanding and insight into “how things are”.

At the archaic stage (emerging ~250,000 years ago), humans were becoming self-aware, inventing fire, mostly acting on instinct and primarily focused on fighting to survive another day.

At the magic stage (emerging ~50,000 years), humans banded together in indigenous families, perceiving their surroundings mostly as a world inhabited by spirits that needed to be appeased. Central values were the family community and magic rituals to cope with any phenomena of their environment they didn’t understand. We still have some societies like this today in places like the Amazon forest or the like, and there are laws to leave them alone because they would not be able to cope with being catapulted into the modern world.

At the hero stage (emerging ~5,000 ago) we have the age of warlords and warrior cities/nations, exemplified by Sparta vs. Greece, Genghis Khan, the Vikings as well as modern despots or ISIS. Any mafia family and street gang still lives at this level of consciousness. The primary values are to advance the interest of one’s own group at the expense of the others. There are always winners and losers (seen unemphatically as a rule of nature), religion is practiced with a sentiment of ‘my god is stronger than yours’ or ‘god will give us victory over our enemies’. It’s a ruthless, self-centered and very bloody affair, and the only way to contain its excesses is through the next stage of consciousness that humans developed into:

At the absolutistic stage (emerging ~2000 years ago) we see the introduction of the law & order state to curb all the bloodshed from the tribal wars. A clear set of (often very harsh) laws, rules and contracts governed by hierarchical institutions and courts ensure a more orderly functioning of society. God becomes a judge living up high who rewards the rule-followers with heaven and punishes the rule-breakers with hell. The Greek and Roman Empires, the Chinese Dynasties, the Catholic Church, the British Empire or the Amish society today are examples of this. A large part of the world lives at this stage today, particularly within traditional Catholic or Evangelical Christianity, Judaism, Hinduism, or Islam. At this stage of consciousness, the primary values are the belief in the ruling truth (the law, the Bible, the Koran, etc.), adherence to its rules and norms, and staying within the role society has assigned to you. The excesses of this are of inquisition, cast systems, Sharia law, colonialism and all the ugly stuff that has been done throughout history in the name of ‘the law’. It is a very stifling and suffocating environment, and therefore the thinking of individuals evolved as they tried to break free, opening the doors to the modern stage.

At the modern stage (emerging ~500 years ago), people started reclaiming their individuality expressed by a breaking free from stale religious norms (Reformation) or passionately rejecting religion altogether (Marx or new Atheists like Dawkins), demanding a say in the rule that govern them (Democracy), turned their attention to what can be seen and measured (Enlightenment and the Scientific Revolution) and focused on the pursuit of individual liberty, prosperity and happiness (Capitalism). Its values are rationality, scientific evidence, individual enterprise pursuing material success and hedonistic enjoyment. This stage brought about incredible advances for human knowledge and prosperity, but also resulted in massive exploitation of the environment and our fellow humans across the globe, demonstrating that its trajectory is unsustainable for humankind to survive on a planet with finite resources. A large part of industrialized and emerging market countries today predominantly work like this, it’s the world all of us grew up in. However, the modern consciousness is not able to answer questions about issues that cannot be measured by science or money, such love, friendship, community or meaning, which is why human thinking evolved further:

At the post-modern stage (emerging ~150 years ago) people realized that living life purely based on scientific facts and material success remains empty, and that there are other, more important things to life, such as community, peace and love. It marks the birth of Albert Schweitzer’s “Reverence for Life”, the UN, the civil rights movement, the environmentalist movement, feminism, hippie culture, etc. The dominant values at this stage are peaceful community, inclusion of everyone, the rejection of the idea of absolute truths, sensitivity to other cultures and experiences, and the pursuit of world-centric (rather than ethnocentric) diversity. This consciousness introduced a new sense of compassion, and since the end of WWII enabled the most peaceful and collaborative era in the history of humankind. However, as every stage before, this stage too has its own limitations, namely its dismissal of fundamental economic principles such as markets and entrepreneurship, the assault on liberties in the name of diversity and inclusion, and its paradoxical tendency to elevate the rejection of absolute truths to an absolute truth itself. Post-modern (groups of) societies today are found predominantly in Northern and Western Europe, Canada and blue states/sanctuary cities in the US, as well as urban hubs in emerging economies. (As a side note, Communism in this model is best understood as a tragic attempt to impose the modern value of materialistic Atheism along with some post-modern values like inclusion and equality (not diversity though!) with the radical means of a absolutistic law & order society. A very toxic cocktail).

Now, all of these stages have in common that they vigorously fight both the previous stage (the one they transcended and which they view as fully obsolete) and the successor stage (the one they don’t understand yet and feel threatened by), and claim their own consciousness is “the right” way to look at the world. When in fact, each stage is just that: A stage on the great conveyor belt of history that is advancing the development of human consciousness. Yet they can’t see that, and mostly stay trapped within their own paradigms, which is the primary cause for all the fruitless arguments and tribal polarization we see on social media. Political discussions today feel like a stalemate, where no one is willing or able to give ground. The only way to transcend this, is by the next stage of consciousness:

At the integral stage (emerging ~50 years ago) people for the first time in human history started recognizing and reflecting on the fact, that there are such things as development stages. That each of us is bound by the indoctrination of our own upbringing, our own culture, our own lens of looking at the world. And in doing so, they realize that all the opinions and views of all these previous stages are not a matter of right and wrong, but merely a natural expression of the stage these societies are at. We don’t laugh at a toddler because he believes in Santa Claus, but instead even encourage this view because we know it’s a natural way for a toddler to look at the world, and he will grow out of this stage eventually. And yes, we get mad sometimes at the volatile behavior and black/white thinking of our teenage kids, but we know it’s how they see the world and it’s part of what they have to go through to become an adult. Applying this way of thinking to human societies as a whole, we suddenly realize we don’t have to be mad at absolutistic people who believe the world is 6000 years old, or modern people who believe individual liberty and capitalism is the pinnacle of human existence, or post-modern people who believe gravity is racist. Instead, we realize that all of these stages introduced crucial new facets to human thinking that transcended the serious limitations and blind spots of earlier stages and advanced human societies as a whole. Our task then, is not anymore to fight and have arguments with people who (over)emphasize any of the other ways of thinking, but to consider what’s worth retaining from each worldview vs. what needs to be thrown out, and integrate those elements into our life and society that make sense in specific situations (hence the word ‘integral’). Then I can invest and build a successful business to earn money (modern), advocate for the environment and the inclusion of marginalized groups (post-modern), while adhering to the necessary rules that govern our peaceful coexistence (absolutistic). Heck I can even decide to go to war (hero) if a specific situation like WWII calls for it. Most of all, I can let go of my preconceived notions that I have “the right” way of looking at the world and be forgiving towards others for their (overly) passionate views. Because everyone’s views are just an expression of the stage they necessarily have to go through in their personal development (and which they will eventually transcend), I don’t have to hate them anymore for it, which is incredibly liberating. And because I know now that even my own thinking in such integral terms will eventually be transcended by yet another stage of human development (one that I don’t understand yet).

For the lefties and righties in my circle, this comes with inconvenient notions though that both won’t like to hear.

For the free market & personal liberty capitalist, it means that in order to move forward in your personal development, you will eventually have to embrace the basic tenets of post-modernism (the fundamental merits of equality, diversity and inclusion, but of course not its excesses like vegan diets, gender-neutral pronouns or believing gravity is racist). Moving forward is the only way to transcend your current worldview, the limitations which causes you (and your fellow human) harm every day.

For the world-centric, environment loving social justice warrior, it means you need to grow to accept that your community-oriented way of looking at the world is not the end-all, but again only an incomplete part of the whole. In order to move forward in your personal development, you will eventually have to accept that some absolutistic and modern principles (like religion, individualism or capitalism) might be crucial elements to living an integrated and full life, and by throwing these babies out of the bathwater, you will do yourself (and your fellow human) harm.

The good news is that this new, integral way of looking at the world and yourself sets you free to be a more relaxed and complete person. Because each of us has all these stages of consciousness in us, and consciously or subconsciously applies them at different times. Acknowledging that notion, fully embracing it and integrating it into our daily lives allows us to get closer to becoming the humans we truly are.

We are both underestimating and overestimating the dynamics of Artificial Intelligence for KM: My 2 cents featured in the updated Agenda Knowledge for Development (K4D)

noreply@blogger.com (Stepping Higher - Reflections on the Knowledge Age) — Fri, 28 Sep 2018 03:36:00 +0000

Today the Knowledge for Development Partnership (K4D) initiative released an updated version of the 'Agenda Knowledge for Development', which formulates 14 "knowledge goals" meant to supplement the UN's Sustainable Development Goals and strengthen the Agenda 2030 from a Knowledge Management perspective.

The updated version includes one added Goal 14 ‘The arts and culture are central to knowledge societies', as well as 57 added statements (in addition to the 73 statements in the previous edition) from knowledge management practitioners in development across the world, including my own.

I've already shared on this blog my reflections on the role that I believe Artificial Intelligence will play in Knowledge Management in the coming years, and I've re-iterated my view on this in my statement for K4D which is now featured under Part II of this document (page 84), "Statements on Knowledge for Development" next to the statements from 130 of my fellow KM colleagues:

"It is easy to hail knowledge as ultimate driver for change and key resource to achieve the SDGs. The sobering reality, however, is that more knowledge doesn’t per se make the world a better place. In fact, one can argue that humankind has reached a point in history where there is more knowledge than it can productively handle. Despite the known benefits of democracy, support for democratic principles is shrinking worldwide. Despite the advances to human progress through science, increasing portions of populations wilfully choose ignorance and ideology over scientific evidence. And despite unprecedented access to news and information sources, consumers chose to rely on fake news instead of fact checking. These are symptoms of a world in which there is just too much information for the human brain to meaningfully process. And the instinctive response is to retreat to what we already know and are comfortable with, rather than expose ourselves continuously to a complex world in which discerning the best route of action among many truths is very hard work and just plain exhausting.

One way in which humans will try to resolve this in the next decade is that we will turn to Artificial
Intelligence (AI) to sift through the massive amounts of knowledge and information available, and make sense of it for us. As with past tech trends, we are currently both underestimating and overestimating the dynamics of this technology in the way we manage knowledge. We are underestimating the profound transformational impact AI will have on the way we learn about, curate and analyze examples and insights from worldwide activities in our everyday work. And we are at the same time overestimating the extent to which technology can solve our underlying problem of using knowledge to better the human condition. Programmed biases in AI systems, questions of legitimacy and over-reliance on ‘black box’ AIs, and issues around ethics and local context are just some of the problems that we will have to resolve as we will increasingly rely on machine learning. Knowledge for development needs to be mindful of the issues that knowledge complexity is triggering in societies, and brace itself for the full force of the AI revolution that will transform the way we manage this knowledge in the upcoming 10-15 years so that we, as development practitioners, are well positioned to both reap its benefits and mitigate its pitfalls as we work towards achieving the SDGs."

What do you think? Is this view too much preoccupied with the current global political context, which may be more of a momentary snapshot than a long trend, or do you agree that the dichonomy between information availability and capacity to dicern and process it will be the key KM challenge of the years to come?

How to program for uncertain results? The innovation journey of a 'slightly unsusual' programme in UNDP

noreply@blogger.com (Stepping Higher - Reflections on the Knowledge Age) — Tue, 27 Feb 2018 04:21:00 +0000

Innovations are driven by risk-takers. Part of UNDP’s role in innovation is to provide the space for risk-takers to develop and test their ideas. And it turns out that sometimes these are not individuals, but entire programmes! The Pacific Risk Resilience Programme (PRRP) covers the Pacific countries of Fiji, Solomon Islands, Tonga and Vanuatu, and takes an unusual approach within UNDP’s programme portfolio. Now in its fourth year, it didn’t exactly follow the standard programming approach in which a challenge and a development model is identified in the beginning, and a set of interventions is designed that would then be rolled out over the course of the next years, with clear activities and results prescribed for each year. Instead, PRRP didn’t actually describe the model or the interventions themselves at all. Instead, they let the model emerge over time by running sprints of interventions and evaluating them frequently, something that is known in the information technology world as ‘agile development’. I've talked to the programme manager, Moortaza Jiwanji, about their approach, what they learned from doing things differently, and the implications of their experience for UNDP programming.

Q: Why did you feel the need to do things differently than in ‘traditional’ programming?

The main reason was that we that we had to develop something for which there was no precedent. We were venturing into unknown territory, and it made little sense for us to prescribe what results would look like 4-years in advance with a results framework that pretends to know exactly what activity would be best to deliver by year 4. We simply couldn’t see how that would work.

Climate change and disasters have a real impact on people in the Pacific. Despite the unprecedented levels of funding and programming in the region, it is disheartening to see how communities are still experiencing the same types of impacts of climate change and disasters and in some cases, these are becoming worse! This is particularly concerning given that the symptoms of climate change such as cyclones, flooding and droughts are likely to increase in intensity and frequency in the future.

Much of this programming in the Pacific has led to some concrete results on the ground, but we felt that there was not enough thought being put into addressing the root causes of these vulnerabilities. It is less obvious to see how development itself is being adjusted to address these risks. For instance, why is it that schools and houses are still built in flood prone areas without the appropriate materials and design codes? It is also becoming increasingly clear that development itself is a primary cause of this vulnerability to climate change. This could perhaps explain the cyclical nature of these impacts.

We realized that something needed to change within development itself and not just in climate change programming. Most programming is focused on technical solutions such as building sea-walls rather than dealing with the root causes. It seemed at the time that there was not much programming experience in dealing with climate change from a ‘development’ perspective. We knew what needed to change but there was limited experience in the region and globally to show us how.

That’s why we decided to develop a model for risk-informed development without any preconceived ideas about what it would look like and how it would work. Our starting point was to address deep-seated governance issues, not for climate change, but for development. We also felt that this would be an opportunity for UNDP to build a niche for itself, particularly given that we are a ‘development’ agency and also deal with governance reform. We were able to do this through the Pacific Risk Resilience Programme (PRRP) which started in 2013. PRRP was funded by the Australian government as they also felt willing to try something different given that they were also not seeing the aggregate results in the region.

Q: What exactly was ‘different’ about your approach?

We knew we had to do two things differently: First, in order to tackle the root causes of climate change and disaster risk, we had to work deep within development itself. And second, because at the time back in 2013 there was not much experience of dealing with climate and disaster risk from a truly ‘development’ perspective, we had to follow an approach that was largely experimental at the time and depart from more traditional approaches to programme design and implementation.

So what was different about our approach? First, unlike most development partners in this area we did not work as an outside partner with climate change and disaster management functions in government. Instead we programmed ‘from within’ governance systems where our government partners owned the development interventions from community to national level. We also used a human-centered design approach that really focused on developing individual mechanisms with the same people that were going to apply them in their government ministries and agencies. Both these aspects allowed our country partners to help design and fully lead the initiatives themselves rather than UNDP leading the way. This admittedly raised some eyebrows at the time as there was an expectation for climate change to work with (and provide funding for) the ‘usual suspects’.

Figure 1: The Innovation Feedback Loop

Second, unlike standard programme design approaches we did not predetermine our activities and outputs well in advance for the next four years. Instead we built smaller and targeted experimental interventions where we saw some prospects of success (see adjacent diagram), e.g. where we found receptive partners and conducive political environments. This allowed us to understand which activities did yield the best results as we implemented them. We then spent a great deal of time and energy in measuring any apparent successes and even more importantly failures. Learning from these experiences was the most important ingredient and we spent a great deal of time and energy on doing this collectively with our partners. So whether a pilot leads to measurable successes or failures, the real success of this approach comes in how well you learn and subsequently redesign and modify approaches based on these learnings. Based on this iterative process we would then develop the overarching model as it emergedfrom those experiences. The interesting thing about this experience is that we developed this modus operandi ourselves, completely unaware that UNDP was promoting through its global Innovation Facility exactly such innovation and design approaches that encourage this type of experimentation. At the time of designing this programme back in 2013 we decided to call this approach ‘emergent design’, but it aligns very much with the innovation principles of agile development and problem-driven adaptive iteration.

Based on the learning from these experiments, we have now developed an overarching model around the concept of ‘risk governance’, designed and tested to risk-inform development ‘from within’ and at all levels of governance. For more information you can read our recently launched policy brief and you can also see practical examples of how this is benefiting countries in the Pacific on our website www.pacific-prrp.org.

Q: What were the challenges you encountered?

Risky business. Developing a programme based on emergent design or agile development principles is extremely exciting. However, it can also be quite stressful because in essence you are taking a significant risk in programming something that has not been tested successfully yet. This is particularly challenging when it comes to convincing your programme stakeholders, such as your donor, country partners and even internal management.

Raising eyebrows. In the early days, we seemed to develop somewhat of a reputation as being the slightly unusual programme within UNDP. This was not always cast in a positive light and this is partly because we did not have a fixed and clearly defined results and resources framework over a four-year period.

Buy-in from stakeholders. There are three types of stakeholders that we dealt with through this experience: the country partners (or beneficiaries); our donor partner; and UNDP itself. The approach of working from within and building governance systems to risk-inform development was most positively received by our government and donor partners and then eventually with our managers within UNDP. This took a little while perhaps largely because we were venturing into the unknown and did not have a clear narrative to describe and justify our approach, particularly in the early days.

It can take some time to show predictable and regular results. Agile development or emergent design approaches can take some time to achieve tangible results. It is almost by definition impossible to predict when and how results are going to be achieved. This was particularly challenging when working in an environment where programmes are expected to report on results against clearly defined outputs and targets at least every quarter.

Q: What were the benefits of taking this approach compared to more traditional approaches?

In essence, agile development allowed us to get results that otherwise would have never emerged had we prescribed our specific outputs the traditional way several years in advance. And on top of it, the solutions that we did get through the agile development approach now address the actual problem we’re trying to tackle much better.

Over time we saw that taking this approach was extremely beneficial, particularly to our government partners, in offering more sustainable and realistic solutions to the complexities of climate change and disasters in the Pacific. You can see this by the fact that our country partners are now advocating for this approach within their own countries.

Unexpected solutions. What’s really interesting is that taking this approach has led to solutions that we would have never designed up front. For instance, we now have Ministries of Women leading on climate-informing community development initiatives. Private sector networks are now being formed to not only work better together in times of disasters but also to provide a more effective link with government and partners. Local governments are leading the way in risk-informing infrastructure projects. You can see these examples and others on our website under ‘Results’ on www.pacific-prrp.org.

Ability to adapt. Secondly, most of our country partners have really appreciated the ability of UNDP to adapt to a constantly changing environment. They often feel that projects that have fixed activities and outputs for a four-year time horizon are unrealistic and can compromise their own ability to initiate real change on the ground. What we see now is that our partners are leading the way and collectively we continue to discover new innovations.

Finally, taking this approach to development programming is immensely rewarding both on a professional and personal level. It almost feels as if there is no other way to deal with the complexities of development in the Pacific and even beyond.

Q: What would you recommend to others who want to take this approach?

I would recommend four key things. First, don’t be afraid to fail and be completely open about this to your partners. This is critical in finding innovative solutions to complex development challenges. Secondly, invest in smaller and manageable initiatives through prototypes. This will help minimize your risks and allow for real creativity. Third, you will have to tailor your results framework in a way that you frame your described activities and outputs as e.g. number of experiments run and evaluated, number of experiments identified for scaling up, etc., rather that describing up front what these experimental interventions will specifically look like. This will give you the leeway to explore uncommon and innovative solutions, while at the same time hold yourself accountable to measurable milestones within this agile development journey. Finally, taking a leap into the unknown can be risky and cause negative perceptions of your work around you. Develop a small group of like-minded colleagues from within and outside the organization who are genuinely willing to try this out and support you. At the same time, it is imperative to engage management early on in an open but confident way about what you are doing and why.

Q: What could all this mean for the future of UNDP’s programming?

We had very interesting conversations with counterparts within institutional donor organizations who frankly told us that refining this agile development approach further could be very rewarding for UNDP. It would allow the organization to position itself as a unique implementing partner that can offer a different way of programming than most other implementation contractors, especially in programmes that try to tackle government reform issues. I feel that the future for UNDP and similar organisations working in this space lies in innovating its programming itself through such agile development, or ‘emergent design’ principles. Not exclusively, but at least as part of its portfolio. Not only is there a lack of this approach in the development space, but more country partners will want this because it is particularly suited to addresses complex development challenges for which no clear solutions exist yet. This needs to go beyond mimicry though and requires fundamental behavioral shifts in terms of how we design, execute and evaluate our work. But the outcomes are worth it. As I said, this has been the most rewarding professional and personal experience for me so far.

Artificial Intelligence will change Knowledge Management as we know it

noreply@blogger.com (Stepping Higher - Reflections on the Knowledge Age) — Tue, 16 Jan 2018 09:43:00 +0000

I recently came across this blog post by a start-up that is developing an Artificial Intelligence that is being trained to read and write at the level of a specialized human analyst and produce briefings in human language based on a set of different information resources. It’s just one example of many different companies that are currently working on this challenge. The obvious clients are intelligence agencies, governments, or news agencies, but eventually this will enter all of our everyday work very soon.

I thoroughly believe that this is what knowledge management in large organizations will look like in 10-15 years from now. In my organization, we’re challenged daily to consolidate the key lessons and insights from all our country-level programmes and experiences, lest meaningfully combine them with information, trends and insights from the larger development sector. We complain that we’re overwhelmed by the information overload that social media, Yammer and knowledge networks impose on us, and retreat to focusing on a narrow set of information that confirms our biases, pretending we know what we need to know, when in fact we always only have a small piece of the puzzle. Artificial Intelligence promises to overcome this dilemma, as it will have immediate access to all information available, and can do the necessary analysis for us.

We might not be quite there yet to make this practical for organizations like UNDP, but we’re getting closer and closer. Last year we as UNDP KM team at HQ engaged with a well-known AI systems provider, and while both organizations were not quite ready yet to commit partnering on an AI system that can make sense of unstructured texts, trends, insights and lessons in the development sector, will have to get real about this soon if we as an organization want to be ready for what is to come. To quote the same article above: “With technology that can read and write, you have the flexibility to generate custom insights in any format or level of detail. If you’re a subject matter expert, Primer can tell you a detailed story that takes your knowledge into account. If you’re new to a subject, it can generate an introduction to get you up to speed quickly. If you have an interest in a particular angle on the story, or a geographic lens that you want to zoom in on, the insight can be customized for you. Imagine the possibilities if you had one thousand analysts working for you, all day, every single day. What questions would you ask, what kinds of briefings would you have them prepare?”

Now, technology can always only be one part of the solution. It is important to keep in mind Dave Snowden’s adage that if you have $1 to invest in KM, invest 99 cents in connecting your employees over shared opportunities and 1 cent on content. Connecting people has always been (and will always be) at the center of knowledge management, where we try to connect staff to those who have the skills, capacitating them to identify the right people, enable them to collaborate and research in real time and turn the result of that into actionable insights. It’s why other UN organizations have often looked to UNDP for KM advice, because it regularly chose to make strategic investments in connecting and fostering networking among its staff, being the first UN agency to pioneer email-based knowledge networks in 1999, the first to introduce organization-wide corporate social networking with its award-winning platform Teamworks in 2009, and continuing that trajectory with Yammer (among other things) today. Connected people are the ‘operating system’ of any meaningful KM effort that allows real-time collaboration within a human context that can be turned into actionable insights.

But what forefront thinkers in the AI space tell us about AI’s implication for governments is true for international organizations like UNDP as well: AI will relieve knowledge workers form drudgery tasks, split up our work into automated tasks (e.g. research, collation) and human tasks (value-based decision making, social interactions), and augment the capacities of knowledge workers by adding layers of real-time and predictive analysis that humans couldn’t do by themselves. Together with many of my KM colleagues who are much more skeptical about AI than I am, I also believe the focus will be on augmentation, not replacement. Nonetheless, all indications suggest that we are at the beginning of a revolution of how knowledge work looks like, and organizations like UNDP will be affected internally by both the benefits and risks. The only way to get ourselves ready for it, is by doing what the innovation community always does: Striving to get our feet wet early, and learn, learn, learn.

Who is Reading UNDP’s Publications, And Why?

noreply@blogger.com (Stepping Higher - Reflections on the Knowledge Age) — Tue, 04 Oct 2016 20:54:00 +0000

[This post was originally published at UNDP.org on Oct 3, 2016]

It has been two years since the World Bank published a report that stated that over 30 percent of its policy reports have never been downloaded even once and only 13 percent of policy reports were downloaded at least 250 times. The debate among development practitioners that followed made it clear that the World Bank is by far not alone with this phenomenon and that most international organizations, including UNDP, face the exact same challenge.

As UNDP provides support services for implementation of the Sustainable Development Goals (SDGs), we in UNDP’s Knowledge Management Team see the importance of getting insights into the perceived value of our knowledge products and therefore UNDP’s thought leadership in various SDG topics.

In fact, UNDP’s Knowledge Management Strategy 2014-2017 pointed out that UNDP needs to invest in its process of planning, developing and disseminating knowledge products in ways that make them “more relevant to clients’ needs, more flexible and timely in their development and format, and more measurable in their quality and impact.”

During the debate that followed the World Bank’s report, we the Knowledge Management Team at UNDP thought long and hard how to get meaningful data about who is actually reading its publications, to what extent those readers find individual publications useful, and most importantly, for what end those products are actually being used. In order to do this right one would almost need to talk to each individual reader and ask them one by one, which is kind of impossible on an ongoing basis. Or is it?

Well, after several prototypes and tests during the last year, we’ve finally come up with a model to do just that. In March 2016, we tweaked UNDP’s Public Library of Publications so it would present users with a post-download pop-up asking them whether they would be willing to leave their email address so we could contact them later.

In the six month since we introduced this question, over 42,000 users left us their email addresses, and we since followed up with 27,000 of them (through a weekly survey issued a few weeks after a download of a specific publication), asking them how useful they found the specific document they downloaded, what organization they are with, and whether/how the publication made a difference in their work. As of September 2016 we received 1186 survey responses, and the insights we get from our audience goes far and beyond any of the intel we had in the past.

We can now see how useful our publications are to our users, and to what extent specific publications reflect on UNDP’s thought leadership in that topic:

Even with the possibility of a voluntary response bias, the numbers serve as a valuable baseline to track changes in perceived usefulness over time. In addition, we now for the first time get a clear picture who is getting value out of our publications:

And most importantly, we learn from our audience how and for what purpose they use the downloaded publications in their work:

We are also getting great qualitative feedback on how we can improve specific publications in the future, and the individual comments provide great anecdotal evidence at project or community level that demonstrate the impact of UNDP’s work on the ground. Here are some of the impact stories we’ve received:

“The publication was used in the development of our food security and livelihood strategy for the Uganda refugee operation.”
“The publication has been useful as a starting point to persuade managers of Nature Reserves and Forest Reserve to consider ecotourism planning besides conventional forest management planning.”
“Some of the inputs were used in our legislative agenda setting, especially those that are applicable to the Philippines situation.”
“I am working in Rwanda’s Environment Management Authority and the publication is useful for public sensitization.”
“I introduce the paper to PhD students in my development administration class and asked them to prepare a paper on SDG targets.”
“The publication was of fundamental importance for the Pedagogical Political Plan formulation for professional training courses developed within my organization, the Military Police of Mato Grosso, Brazil.”

Going forward, we are making this qualitative feedback available to all our staff, so they will be able to look up their publication and go through all the individual comments the publication received. It is this kind of evidence that shows us where investment in the quality of our publications pays out, and where we need to switch gear, improve our efforts, or shift our focus entirely with regards to specific thematic areas. Most of all, it is these stories that inspire us as staff on a daily basis as they remind us why we are doing what we are doing in our pursuit of sustainable human development.

Of course, this measurement approach is only reaching those who download publications online, and will miss out on all those who receive them through hard copies or through presentations at workshops and conferences.

What did your organization do to get feedback from your offline audience, and do you have any suggestions for how UNDP could fine-tune the above measurement approach? Leave comments below, I’d be glad to hear your suggestions!

The “Duh-test”, or what is not a lesson learned

noreply@blogger.com (Stepping Higher - Reflections on the Knowledge Age) — Thu, 18 Jun 2015 19:54:00 +0000

I was recently reviewing a number of texts which my organization collected from past projects and initiatives (some through an internal mandatory monitoring tool, others gathered as part of After Action Reviews or Lessons Learned Papers), which all meant to capture ‘lessons learned’ from specific experiences.

And while these texts were not wrong per se, I realized that there seems to be a fundamental misconception what constitutes a good lesson, and what doesn’t. Here are a few typical examples of what we often collect as part of such lessons learned exercises:

“Ensure that the [Team] Manager has excellent leadership, project and team management skills, understanding of programming and experience working in [the subject matter].”
“Project outputs must be compatible towards project goals. Throughout the project there is a need for careful identification of project goals and outputs to ensure that they are compatible with each other. This can be only ensured through a consultative and participatory approach in project design with target institutions, implementing partner and experts.”
“Managing relationships between key national and international players during [the project activity] is very important. Recognizing and respecting national ownership and leadership of the process is vital and key to winning the trust of the national authorities.”
“The better local authorities are involved in the process, the better the expected results are easily achieved and durable.”

The above examples are representative for a common type of lessons learned write up, which fails to pass what I would call the “Duh-test”:

If a ‘lesson learned’ statement is so obvious that it is self-evident to every reader, and at the same time so generally applicable to almost any type of project or initiative, it basically becomes meaningless.

It is good when a team realizes that it failed to put in place a team leader who has leadership and team management skills (and yes, it should remind itself do better next time), but there is literally no value in sharing that learning point with others outside the team, simply because everyone already knows that this should always be a criteria for selecting team leaders. There is nothing new to learn here that would change anyone’s views or actions.

Also, if a lesson is so generic that it could apply to any scenario, we deprive ourselves of the learning effect that comes from understanding the particular conditions responsible for making your project work or not work, so others can go and try to replicate or avoid those conditions.

Such lessons that are either too obvious or too generally applicable produce ‘lessons learned noise’ because these same lessons are reported from countless projects over and over again, without anyone actually learning from them. At the same time, this noise detracts everyone’s attention from the meaty lessons learned pieces that really provide value to a wider audience.

So what is it that makes lessons learned write-ups actually add value? Maybe asking ourselves the following three questions could help make lessons learned statements worth capturing and sharing:

Will anyone else actually learn something new from this lesson, as opposed to self-evident truths that everyone usually already knows?This is the “Duh-test” and should always be the first criteria.
Is this lesson particularly relevant to your specific situation, as opposed to a lesson that it so general that it would apply to any scenario?The more general a lesson is, the less useful it is.
Does the lesson include or lend itself to a concrete action that you or someone else can take in order to effect a change in future practice? Capturing a lesson is only meaningful if there is an actual change triggered by it

But aren’t the ‘bad’ examples mentioned earlier still true and important to highlight, even if they are not particularly new or context specific? Doesn’t the fact that everyone agrees to them intuitively and that they apply to all our projects and initiatives all the more valuable?

Absolutely! But I would never call them ‘lesson learned’. Rather, these are important principles that anyone should abide by, no matter what subject matter expertise or functional roles someone has. We should treat them as guiding lights for our work, teach them in our training curriculae, communicate them our onboarding and induction sessions and embed them our policy guidance. Some lessons from projects, if they are collected often enough, might eventually be added over time to such a common canon of principles. But we should stop collecting what is already part of that canon over and over again from individual projects, which is no good use of anyone’s time.

What remains after the bonfire: How do we define success of an event?

noreply@blogger.com (Stepping Higher - Reflections on the Knowledge Age) — Mon, 13 Oct 2014 18:09:00 +0000

During the last few weeks I was heavily involved with the SHIFT Week of Innovation Action, a series of parallel events taking place in 21 different country offices. Over 50 practitioners were invited to ‘shift’ from one country office to another to share their experience on innovation methodologies and what they learned from their ongoing innovation projects (many of them funded by UNDP’s Innovation Facility), learn from others, and ‘shift mindsets’ in the process.

As part of the team that coordinated the event week I was in awe of the incredible energy coming from country office colleagues and the enthusiasm, creativity and time commitment on the side of organizers, participants, and the coordination team here in New York. And from the feedback that has been rolling in so far (the evaluation survey shows about 95% of participants were satisfied or very satisfied with the event) it seems the SHIFT initiative was a success all around.

Yet, we all remember other instances of well-organized events which achieved great visibility, but when people were asked there months later what the impact of the event has been, we didn’t have much to show for it.

So you had a nice event that brought people together and left everyone happy and excited, but so what? What came out of it?

I believe we have to be very honest about how we define success of events. Yes, it is good when participants convey in a survey how much they enjoyed the gathering. And it is also great when the event achieves visibility and external recognition with good communication during and immediately after the event, such as national media coverage of the SHIFT hackathon in Belarus, great videos produced about SHIFT events in Haiti, Montenegro or Georgia, or outreach products such as the SHIFT Exposure compilation, that give audiences a glance of what happened.

But it is not enough. Because if 12 months from now, none of the new ideas generated will have inspired actual initiatives, projects or products, if none of the innovative prototypes developed will have been applied in real life, none of the solutions shared will have been successfully replicated or brought to scale, and no one who couldn’t participate in person has a chance to learn from what was discussed the event – then I don’t think we can call the exercise a success.

Then it will just have been a bright bonfire that burned for a single night. We have a nice picture of it, but it will not warm anyone going forward.

So here is what I think is needed to make events worth the investment we put into them in terms of time and money. And please feel free to add your own bullet points to this list:

1. Set up an after-event communication plan, and follow up diligently

Rather than letting organizers and participants disperse after a good event, let’s use the current momentum and excitement when people return to their offices. Make a plan on how we want to communicate the results, increase visibility and leverage the event’s discussions and activities to initiate new collaborations, products and projects. Maybe this is the opportunity to promote an existing Community of Practice (COP), or establish a network of mentors around your topic! Make sure to use all available channels, from internal COPs, to external online networks (LinkedIn, Devex, DGroups, World Bank networks, etc.) to public social media channels (Twitter, Facebook, Slideshare) and try to engage new audiences.

2, Relentlessly focus on knowledge and learning products

Communication products and activities are crucial for getting recognition and visibility, and for reporting back to donors. But the important substance, the ‘meat’ of knowledge and learning points is what others really need in order to apply the results of the event to their work. Where can new colleagues who join the organization six months from now access the video recordings and slides of the presentations given so they can follow the event’s learning points? Where can they find blog posts and short interviews with personal insights and reflections of participants on what they learned at the event and how they intend to apply that to their own work? And where are the hands-on knowledge products that help them review the examples shared and apply the solutions that were discussed? If there are only glossy brochures and good-looking PR videos, but no substantive project examples, how-to articles, lessons learned summaries, guidance notes or toolkits coming out of the event, then we might look good externally, but the event was still a failure for the organization as nobody other the handful of on-site participants will learn anything from it.

3. Track status initiatives and projects coming out of the event

One of the reason we as organizations facilitate working-level events is to fulfil our role as a broker of exchanges to inspire and improve our projects and programming. We must come to an understanding that we cannot afford to organize events that look great from the outside but that do not result in concrete, improved approaches, projects and initiatives that are being replicated and scaled up in other countries and regions. We need to wrap up events with concrete commitments on what will happen next, and be diligent in checking-in with organizers and participants at different intervals after the event on how their commitments, prototypes and follow-up activities are evolving (and no, just planning for the next event to discuss the issue further doesn’t count! ;). That means that as an organization we have to expect more from participants than showing up and consuming presentations, but rather for all to become part of an active knowledge production and application process that extends far beyond the event’s closing session.

This is all much easier said than done. For SHIFT week, our team is trying to practice these points, by setting up an editorial calendar through which we will keep communicating about SHIFT results in the upcoming weeks and months, by supporting the formation of mentor groups for follow-up questions, and by following up with teams on potential knowledge products that could emerge from different events. I know there will be a lot of imperfections along the way, but if at the end of the day there will be more products that others can really learn from such as the Guidance for Project Managers on Crowdfunding, the live-stream recordings from Jamaica and Egypt on design thinking with governments or the top tips and questions from the SHIFT Rwanda coffee learning session, and if brilliant initiatives such as the 112 emergency service for people with hearing and speech impairments in Georgia, the bilateral knowledge exchange on public service centers between Bangladesh and China and others can be turned into re-usable guidance for other countries to build on, then we can truly say that the SHIFT Week of Innovation Action was a huge success.

In your option, what other elements are important for defining success of events?

Rethinking knowledge products after the 'PDF shock': Make them leaner, faster, and never without the community!

noreply@blogger.com (Stepping Higher - Reflections on the Knowledge Age) — Thu, 29 May 2014 20:08:00 +0000

Since the World Bank published its report early this month which states that over 30% of its policy reports have never been downloaded even once (!) and only 13 percent of policy reports were downloaded at least 250 times, a fascinating debate on the purpose and value of knowledge products is flourishing the web, and the posts from KM practitioners all over keep pouring in.

It’s not just the World Bank, but most international organizations

Interestingly, I have been thinking about exactly the same questions for the last 9 months now as I was drafting UNDP’s new Knowledge Management Strategy for the upcoming years. Here’s a passage which captures UNDPs own dilemma regarding knowledge products:

“The current process of knowledge product definition, development, dissemination and measurement does not yield the quality, reach and impact that is needed for UNDP to be a thought leader in development.” The Strategy goes on to stress that UNDP intends to revise its process of planning, developing, and disseminating knowledge products in a way that makes them “more easily accessible, more relevant to clients’ needs, more accountable towards the community they seek to engage, more flexible and timely in their development and format, and more measurable in their quality and impact.”

Format matters

A lot of contributors to the debate, such as the commenters of the respective Washington Post article, the DevPolicy Blog, Crisscrossed or my KM colleagues from the KM4dev network highlight how we have to get much smarter in developing formats that actually appeal to an audience that is increasingly passing on lengthy unappealing reports and paper. And there is a lot of truth to this. Colleagues at UNDP are increasingly learning that short and snappy products, such as blog posts, 2-pagers or infographics will allow communicating important key points from their work to a larger audience and also more just-in-time. Compared with heavy research reports which take months and years to finalize, the advantage of light-weight formats is that they allow for adjusting content quickly as new data and evidence emerges, which makes the product more relevant and timely the moment it is distributed.

The launch of a paper cannot be the end of the project

Ian Thorpe (who arguably came up with the most crisp blog title in the debate so far ;) also makes an excellent point in clarifying that we have to invest much more in dissemination and outreach. All too often the launch of a product is declared the successful end of a research project, when in fact, this should be just the starting point of a whole new phase where we reach out to potential audiences through all possible traditional and social media channels, organize webinars and on-site events to raise awareness of the knowledge product and its key points, and inject ourselves into ongoing debates where our product can add real value. Budgets for development of knowledge products leave this part of the process chronically underfunded, and we as KM practitioners need to make a point that a dissemination and public engagement strategy has to be an integral part of any knowledge production process.

The real issue is the lack of community feedback loops

But while clear abstracts, interesting illustrations, good formatting and focused outreach will go a long way in mitigating the “too long; didn’t read” (TL;DR) problem, my personal belief is that we must pay much more attention to where the problem of unread knowledge products starts: at inception. The Complexia blog nails it when it points out that there is a “lack of demand-driven research” in which “research projects tend to be more driven by the interest of individual researchers”.

How can it be that organizations give authors green light for the development of papers and reports for which they haven’t done any preliminary analysis of what the targeted community needs and whether the product to be developed is likely to find an audience? How is it possible that we can go through an entire cycle of a product production process without probing with the relevant communities of practitioners outside our organizations whether the questions we ask and the conclusions we draw resonate with the audience that is supposed to benefit from them? And not just once in a peer review when the product is almost finished, but at every step, from inception to formulation of research questions, outline and early drafts?

It is clear to me that we need to get rid of our internal navel-gazing posture and get much better at involving the relevant communities much earlier in the process, and at much more frequent intervals than we do today. This is not rocket science, as such ongoing feedback loops can be achieved through regular blog posts about work in progress, a targeted e-discussion at an early stage, and frequent participation in external online fora to vet ideas. But it requires that authors start seeing themselves not as isolated writers, but as facilitators of a larger debate who are tasked to feed the essence of that debate into their product. Authors who make a living of the actual impact of their publications understand this, as you can see from countless books of business advisors and speakers. Authors who are just hired to deliver a product for an organization by a certain deadline (often without even being credited for it) don’t have that incentive.

Are we at international organizations ready to change this? What can we do to turn this pattern around and start thinking about the relevance of knowledge product from the users’ perspective?

Kick-starting Innovation in Response to the Syria Crisis: A Peer Assist Conversation with Arndt Husar and George Hodge

noreply@blogger.com (Stepping Higher - Reflections on the Knowledge Age) — Tue, 22 Apr 2014 16:59:00 +0000

In November 2013 I got deployed for 3 months to Amman on a consulting assignment to support the setup of UNDP’s Sub-Regional Response Facility for the crisis in Syria. A key role of the Facility is to operationalize the Strategic Plan’s key area of ‘Resilience’ in an environment of crisis by marrying the humanitarian response for Syria with a development response. So far there has been a primarily humanitarian angle to the Syria crisis, with OCHA, UNHCR, WFP and FAO leading the response efforts in the region. UNDP’s interest in this situation is to widen the perspective and highlight that there is a dramatic development cost for Syria’s neighbor countries Lebanon, Jordan, Turkey and Iraq, which deal with the largest refugee movement since the WWII. Given that most refugees are not staying in camps are embedded in host communities with families and friends, the host communities face a heavy strain on local services such as access to housing, water, sanitation, health care, education and the labor market, as well as on social cohesion more generally. UNDP finds itself in a situation where it needs to explore new solutions to something that in this scope and in this way hasn’t been done before. This calls for innovation, and my job at the Facility was to help the facility to establish a KM and Innovation framework and action plan to define what the Facility can do from a knowledge and innovation perspective in the next two years, to help UNDP implement a resilience-based response to the Syria crisis.

I have been following UNDP’s work on innovation, and I closely followed the Global Innovation Meeting that took place in November 2013 in Montenegro, including its outputs such the excellent Budva Declaration. Still, much of this to me was rather theoretical and I didn’t have a lot of practical experience on how to approach and manage an innovation initiative. So I contacted a number UNDP colleagues who work on innovation and asked them to participate in Peer Assists – a knowledge management methodology that brings together a group of peers to elicit feedback on a problem, project, or activity, and draw insights from the participants' knowledge and experience (to learn more about Peer Assists, watch this excellent 6 min video here).
I was lucky to win Arndt Husar from the UNDP Global Centre for Public Service Excellence, and George Hodge from the UNDP Country Office in Armenia for a Peer Assist session I conducted in Dec 2013 to tap their brains on implementing innovation initiatives, and I hope the following shortened transcript of the conversation can be of as much help to others as it was to me!

Johannes: I invited you to this conversation, because you both have been involved in practical innovation events and initiatives in UNDP in the past. My hope is to get to a better understanding of the conditions under which certain innovation initiatives make sense and how we would plan for something like this. Where would a team like ours here in Amman start? And what would be the conditions under which it would make sense to have e.g. an innovation camp in one of Syria’s neighbor countries to identify new solutions together with municipalities and local actors?

George: I like that you are trying to incorporate different approaches in addressing these challenges. The first thing I usually do is to get out of the office and talk to municipal officials and the other stakeholders in order to get a better sense of the problems. When running social innovation camps and innovation challenges, the better you can define the problem at the very beginning, the happier you will be about what happens later in the cycle.
If you run an open innovation challenge where you ask “tell us about your problems, and suggest solutions”, you get a better sense of where the problems lie. Whereas if you want to address more concrete problems of your stakeholders, then you should run an innovation camp or challenge around a specific question.
I recommend visiting your stakeholders to get a sense of which public services are under strain. Then you can run a series of concurrent challenges asking “Can you come up with ways in which we can overcome this particular issue”. But if you are at an early stage and you are trying to make sense of the environment, an open challenge may be best. You should expect over 100 responses, and from that you will get a sense of where people see the most pressing problems.

Arndt: That was great feedback from George. I think I need more clarity on the scale: Is this something you want to do at an inter-governmental level, or do you want to look for solutions in each specific country? This will define your immediate counterparts and your outreach. Municipalities are good, because they are the ones delivering your cutting-edge services. You could break your issues in the sub-region down into national challenges, and then go out and do the sensing with local partners. For me the big question is the connection between that massive scale of four countries, and the local services that you are looking at.

Johannes: To give you feedback on the scale, we are talking more or less about three countries: Jordan, Lebanon and Turkey, because those are the three countries that host the biggest population of refugees. They are also at a more advanced development stage with larger middle income population, so we may have a higher chance to get some of those technology solutions with private sector off the ground.

Arndt: Ok, I think that’s very good. This sounds similar to what we had in Singapore with our social innovation camps. We had activities in multiple countries and at the end convened a regional summit where we brought the various countries together to combine different country perspectives, which worked quite well.
Regarding the conditions that have to be in place to organize something like this, Mm experience in our regional initiative in Asia-Pacific was that the outputs depended hugely on the local organizing partner and also on the network that the local partner brought in. If you partner with some agency that has a very specific urban network, then you get that kind of result. If you partner with an agency that has a lot of techies in it, then you are going to get a lot of IT solutions. So it’s really important to pick the right partners (ideally a consortium of partners) so you can have a wider range of solutions.
Another lesson that we learned is that during the short duration of a three day camp people really just scratch the surface. I think if you want to get real solutions from municipalities to be innovative, you need to along the lines George suggested: First the sensing, then the definition of the problem, then the call, then probably some research (almost like the production of a case study), and then you go into prototyping and so on. That’s a really thorough preparation process, which we ourselves were not able to do through just a social innovation camp. The above requires a bit more work.

George: What Arndt has just identified is why we – after running a few Social Innovation Camps – decided to set up an Innovation Lab, because we realized we needed a bigger support structure around our events. You need to do the sense making first and then come up with a series of really specific challenges - this will give you results that are much better aligned with your mission.
After the first social innovation camp, we gave the teams grants and just said “good luck, come to us of you have any problems”, but this approach is too passive. By now we have a much bigger support structure where we get our hands dirty with the teams and actively invest in the initiatives that pass through the lab – much more like a incubator.

Johannes: So how many of these three-day social innovation camps in Armenia did you run? And have they all been successful?

George: We have run four of them, and they were definitely worth it. I would say if you run a three-day event, it is useful to look at what is already out there of which UNDP is not aware, and identify people who have a deep understanding of the social problems in question. Maybe there are teams that are already established, but don’t know how to scale their activities, in which case you could throw UNDP’s institutional weight behind an initiative and scale it quickly.

Johannes: And then you can go a step further and turn that to a ‘lab’ structure. What is a lab exactly?
George: It’s an incubator for social projects where we mimic business incubators: Identify ideas, conduct rapid prototyping, get a very basic product into the world, test it with users, and then look at the feedback. Is this working? Is this gaining traction? If yes, let’s invest more! And all the while you are giving the team access to mentors and design workshops, and develop their capacity. With a lab you can test multiple ideas and hypotheses at the same time, look for results, and then scale. This is very different to traditional programming approaches. The lab in Armenia attempts to solve big social challenges by harnessing citizens’ experiences, insights and ideas alongside public services. It applies approaches like horizon scanning, design challenges, user-innovation and service design.

Johannes: And what does it take? How much does it cost and how many people are involved?

George: Social Innovation Camps all-in-all cost about $25,000 here in Armenia. The event team should include an Event Coordinator working part-time, plus a full-time assistant, plus a full-time intern over the course of four months. And all that a Lab does is to extend this team people on an ongoing basis.
In terms of time you are looking at four months from the launch of the call for ideas until the event itself. During the preparation phase the team goes out running workshops, talking to people and developing ideas about the problems or challenges. Once the applications come in, they are also looking to find the experts that will complement the idea owners. For example, we had a doctor approach us who said she wanted to digitize Armenia’s blood registry. Of course she had no idea of how to build a database and how to build a web interface. She was just a doctor who understood the problem and had an idea how it could be fixed. So the organizing team then goes out and finds the extra skill sets and people needed to build a crude prototype of the initiative (in this case an online blood registry database) at the event.

Johannes: But even that is a lot of things to do in just four months.

Arndt: Well, in your case we may need to rethink the whole approach. For emergency response situations you need to get to solutions much more rapidly. It is almost like ignoring what Design Thinking says: You have to give it time through various iterations. But you are in a situation where you need quick solution which you can rapidly scale up. Maybe we need to design a process that can be more integrated into government and existing institutions, so we skip the part of building a team. Instead we do stakeholder engagement, and bring in NGOs, relief organizations and governments, host community and refugee representatives and come up with something that can be immediately picked up by the municipalities. Thereby you could crunch the time that you would usually need for the incubation.
George: But then, it is still an untested idea, and the whole point is to establish whether an idea works.

Arndt: Yes, you would still have to test that idea and develop it further.

George: Another idea that builds on Arndt’s could be to do an open call for existing initiatives that are already working on a pre-defined problem. If they have developed a prototype which has generated results we can help them scale up. You are basically looking to adopt alpha or beta products in the late stages of development. You can apply the same skill sets that you would need for a Social Innovation Camp, but you get to scale faster. The challenge is finding these existing initiatives.

Johannes: How do you identify who you can actually talk to? It’s not like you have in a Country Office a list ready with all the actors that you could potentially approach on specific issues.

George: Well, I would start with whatever list you have, and talk to them. First you talk about the problems they face and then you ask them who else they know in their network who is good at addressing this kind of issue, and contact them as well. Repeat this process until you find existing initiatives or citizens who are addressing the problems in creative ways.

Arndt: In your case in Amman, the approach is really a lot about user experiences, either from refugees that are coming from other countries, or the host communities. Think of who has the best information and can identify the crunch points for which you want to develop solutions. Then interview people and collect stories, so you do the sensing exercise in that particular environment that surrounds the issue you are looking at.

Johannes: In both the Armenia Social Innovation Camps and in the regional camps in Singapore, who did that sensing. Was it both of you, or did you hire consultants to do that?

Arndt: In our case it only happened in one camp, and I must say, that we didn’t go with the standard Social Innovation Camp approach because it didn’t do as much of sensing. It basically relied on the participants, the idea givers, to do that. Some of them had done a decent job, but a lot of them had not. The one camp that did this really quite well was the one in Singapore where we had a local counterpart institution that had the mandate to engage on this in the long term, and they did a fantastic job on this.

George: In the case of Armenia, we did it in a team of three: a consultant, an intern and me. The three of us travelled across the country delivering the sensing workshops. Because as Arndt rightly highlighted, you need to get a lot of different perspectives on the problem. I recommend keeping the team in-house instead of giving it to contractors, so you can develop and keep the knowledge, relationships and networks. Also, if you outsource there can be issues of quality assurance. It takes a little bit more work, but at the same time, it really supercharges your learning. We now have an entire list of organizations and people with whom we would never have developed relationships had we not run the event and the lab in-house.

Arndt: It sounds to me that if you want to do a three country project, it will be a quite elaborate process. If you want to create real value it make sense to invest some funds into it and have people do it full time.

Johannes: Do you think it is better to start off with only one country, rather than doing it in three countries at once?

George: It depends on how you are going to do it. If you do it in-house start with one country and make sure you build the skills within the team. But if you are going to outsource it, you might as well go big from the start.

Arndt: I would tend to say go big, because for the Sub-Regional Facility, that will prove your value.

Johannes: Well, it’s not like I am going to do this outreach myself, I am here on a detail assignment for another few weeks. But what I need to do is to put the train on the rails and a plan in place so the Facility can hire someone full time to take that plan and run with it.

Arndt: The other thing is: So far we only looked at the option of Social Innovation Camps at the grassroots level. The other possibility is to think of this rather as a public service initiative in support of an innovation-type exercise. You can look at examples of Policy Labs that were presented in at the Global Innovation Meeting in Montenegro, and now again at our event in Singapore, such as like the Mind Lab (Denmark) or designGov (Australia). The latter is more a governmental initiative which also applies a design thinking approach where it is government officials who do all the sensing. They have almost a purely government-driven lab, but they hire service providers which will accompany this process. I wouldn’t be surprised if some of Syria’s neighboring countries had a few companies providing design thinking consultancy services that you can hire to facilitate governments finding solutions. This is different than just coming up with a solution from a UNDP office and then developing a pilot, which is the traditional way UNDP does business. Instead, it means that people really go down to the ground level, get a sense of problems, go back and develop prototypes, test them out, and then scale up what works.

Johannes: In the case of Singapore, did the government already have something like that in place, or did they ask UNDP to help them establish the lab?

Arndt: Here in Singapore the Human Experience Lab (THE) Lab is a relatively recent initiative, while Denmark, Australia and UK have policy labs since while. The Singapore lab is only half a year old, but they have been practicing design thinking for a bit longer. Supporting such government labs is possibly an alternative option for UNDP, although these modalities don’t necessarily exclude each other. You could have a government-driven process going on, with social innovation camps as satellite events. That would be really nice because the innovation camps could feed into an official government-driven process and you could have a dialogue between the processes. That might actually be even better than each modality on its own. But of course you need more money for that.

Johannes: From your experience, how many of these solutions that come out of such modalities are IT-driven, like Web 2.0 or e-government solutions, and how many of them are non-tech, like processes or policies?

Arndt: The social innovation camps I’ve seen were almost all tech, but that is because we had specifically asked for tech. The output from the government lab was mostly non-tech, such as project re-engineering, cutting silos, cutting bureaucracy, finding new ways of communication with citizens, etc.

George: From its origin, the specific objective of social innovation camps is to apply Web 2.0 to social problems. So if you are looking beyond tech then you are looking at innovation challenges or design teams. Service design approaches do not involve crowd sourcing but can be a good way of generating lots of ideas for alternative approaches to service delivery. You certainly get non-tech solutions emerging from this. However, if you embrace an open process and just collect ideas, it actually doesn’t matter whether the solutions are IT-based or not. The point is: if you open up to many different inputs, you get good ideas.
Arndt: I second that. It is also easier to scale if the solution is non-tech.

Johannes: From all that you said, I understand that at one point we will have to make that national , regional or global call when you put the question out there who has a solution to a particular problem. How do you actually plan for that?

George: From our experience here in Armenia, once you have a sense of a problem, you can either do an open challenge where you say “tell us about problems and suggest solutions” or a slightly more specific one “tell us about problems in this sector and suggest solutions”, or you ask a really focused question like “tell us about solutions for this specific problem”. Once you have the question you build a small website and integrate social media into it. Whatever the social media platform of choice is in the country you are working in, focus on the top two. Then you have to go into different communities, both online and offline, and starting talking to people. You can’t just build a beautiful garden and expect people to come, you have to go out and engage with people where they are. Our intern worked very hard going into every single web forum in Armenia she could find, talking to people and looking for activists with whom we could work. Just talking to them at a personal level about the issues, and through that engagement process, a lot of hits were generated on our website, and then turned into applications for the event itself. You then complement that with a series of sensing workshops, where you are targeting specific groups of stakeholders. In your example you would talk to host communities, refugees, to state officials, municipal officials – especially in front line service delivery, and journalists. You invite them to a workshop where you ask them to define the problem more clearly. Or if you have already identified the question or challenge, you let them brainstorm on solutions. You also ask them “who do you know who is already working in this”, so you can meet them and see if you can support their work. From that engagement process you will get a lot of connections and ideas. Then you take the best 5 or 6 ideas into a prototyping event, much like a social innovation camp.

Johannes: Well, thank you so much guys, this all really helps our thinking here a lot. We will have to develop an action plan on this going forward. I will write this up, both in a blog but also in the form of some concept note for the Facility. And I’ll keep you updated on how I can inject those thoughts into what we are doing at the Facility, and we’ll be happy to share how far we will have come with it in a few months’ time!

Figuring out where to begin: How to do KM for a start-up business unit (Part 3)

noreply@blogger.com (Stepping Higher - Reflections on the Knowledge Age) — Mon, 31 Mar 2014 18:03:00 +0000

Following my earlier posts on my assignment with the Sub-Regional Response Facility for Syria in Amman, Jordan, where we identified the general directions for KM for this business unit, here are now the details of the KM plan that I introduced, based on our earlier needs assessment.

1. An Online Collaboration Space for the Facility, targeted at the Regional Working Group and invited guests

To support of the Facility’s role as a broker, the creation of an online collaboration space hosted by the Sub-Regional Facility will allow the team to provide an online home for the Regional UNDG Working Group for the Arab States/MENA to share draft papers and relevant resources on an ongoing basis. Even more it creates a space to discuss questions and collect comments from colleagues on the Facility’s ongoing work. In the spirit of ‘working out loud’ we will also invite a number of selected colleagues from all UNDG agencies into this space.

2. Establishment of a UNDG-wide Community of Practice on Resilience-Based Development, including selected guests from academia

A key element of the Facility’s broker function is fostering a Community of Practice of colleagues working on resilience in context of humanitarian and development work. The Facility will use the above space as a launch pad for e-discussions and ad-hoc queries and benefit from the input of UN colleagues. A first formal e-discussion on vulnerability criteria has already taken place in December 2013, and the Facility will reach out to selected experts in the field of resilience, humanitarian work, local governance, etc., followed by additional discussions and surveys among the new community members in 2014.

3. Mapping of stakeholders for research on resilience and partners for engagement on Resilience-Based Development

In order to identify relevant stakeholders that the Facility can engage and work with in its role as a knowledge broker, a knowledge mapping exercise is recommended. This will be targeted at two levels:

Mapping of potential members for the above Community of Practice on Resilience-Based Development for Syria.
Mapping of stakeholders for collaboration on research, innovation and substantive projects outside the UN system.

4. Exploration of organizing social innovation camps in Jordan, Lebanon and/or Turkey to identify and prototype e-governance solutions for a priority issue (e.g. local services)

UNDP’ experience in the Europe & CIS region suggests that there is great potential in bringing together citizens, local actors and innovative NGOs and companies to identify innovative solutions to local issues that would benefit from the UN’s support in prototyping, testing and scaling up. This can include the Social Innovation Camp methodology and could also be precluded by a public innovation competition to crowd-source practical solutions to local challenges around resilience-based development. Depending on the evaluation of the experience, this could be a precursor to widening the scope of audience and establishing at a later stage an ongoing innovation lab facility in cooperation with one or several of Syria’s neighbour governments, similar to Kolba Labs in Armenia.

5. Series of targeted consultations on questions related to resilience in context of a sub-regional development forum for Syria

In the process of identifying innovative solutions for operationalizing a resilience-based development approach, the Facility should draw on input from a larger audience. UNDP/KICG’s experience with large scale consultations targeted at a large pool of external experts and interest communities, such as the Rio+20 Dialogues or the Post-2016 Consultations have the potential to add significant value to the above process. The objective would be to inform the operationalization process of the resilience-based approach with substantive experiences, suggestions and prioritizations from selected actors in the sub-region, including government planners, public service workers, host and refugee communities, as well as selected civil society organizations and private sector companies.

6. Creation of data visualizations and infographics, to use as communication, advocacy and capacity building tool

Once the resilience-based approach has been operationalized in more detail, the Facility’s dissemination and capacity building efforts will benefit the use of simplified infographics and data visualizations for communication purposes. This is particularly suitable for data-heavy research findings that allow for clear conclusions, narratives and calls to action. This visualizations can then be used in print, video or online knowledge and communication products.

7. Conducting monthly webinars, to periodically inform UNDP and UNDG stakeholders about the Facility’s ongoing work, outputs and results

While the focus of the Facility is on brokering and innovating, there is still a natural need to disseminate results to at least the immediate audiences the Facility is working with, such as UNDP and UNDG agencies. In order to create visibility for the work of the Facility, to communicate results of research, projects, events and initiatives, as well as to foster learning within the Community of Practice, the Facility could host regular online webinars that would serve as both learning and advocacy instrument.

8. Maintaining a regular blog about the Facility’s ongoing work and results, to increase visibility and influence the general debate on resilience

In order to influence the debate on Syria among stakeholders, and ultimately influence decision making of development actors, the value of the tool of blogging cannot be underestimated. Maintaining a regularly updated public blog where different authors provide personal views and reflections based on UNDG’s work can have a significant impact on framing the conversation along the outputs, activities and objectives of the Facility. I order to do this right, the Facility must be committed to publish at least two blog posts per month. This can be reasonably achieved by rotating authors among the facility’s substantive development experts.

9. Peer Assists, applied as needed to get input from peers on internal tasks and challenges of the Facility

A Peer Assist is a KM methodology (see instructional video) that brings together a group of peers (on site or online) to elicit feedback on a problem, project, or activity, and draw lessons from the participants' knowledge and experience. Peer Assists are useful when starting a new activity or project and a team wants to benefit from the advice of more experienced colleagues, or another group that has faced a similar situation in the past.

This methodology is targeted at the Facility internally to improve its own work as a team. The Facility should map the planned projects for the upcoming, determine which of the new projects and initiatives would benefit from a formal Peer Assist, and then identify potential peer experts who could be invited to participate. However, they can also be organized ad-hoc when problems emerge that the team is not quite sure how to address.

10. After-Action Reviews, after key events or activities to reflect on the ongoing work of the Facility and capture learning points

An After Action Review (AAR) is an internal process used by a team to reflect on a recent activity or event to capture learning points with the goal of improving future performance. The facilitator of an AAR will ask the team three questions: “What was supposed to happen?”, “What actually did happen?” and “What can we learn from it?” AARs can also be employed in the course of a project to ‘learn while doing’. They should be carried out with an open spirit and no intent to blame. The American Army, which invented the methodology, used the phrase "leave your rank at the door" to optimize learning in this process. The KM Specialist of the Facility should constantly look out for opportunities to conduct AARs with the team, which can be as brief as 15-30 min, even though AARs of up to 2 hours might be suitable for reflecting on larger projects or events.

Below you can see an overview on how the different suggested KM action items will be rolled out in 2014.

Figuring out where to begin: How to do KM for a start-up business unit (Part 2)

noreply@blogger.com (Stepping Higher - Reflections on the Knowledge Age) — Tue, 21 Jan 2014 16:15:00 +0000

Following my earlier post on my assignment with the Sub-Regional Response Facility for Syria in Amman, Jordan, I'd like to follow up with the results of the needs assessment that we conducted, and the resulting directions for knowledge management that the Facility identified for itself.

Role and audience as prioritized by the Facility
After exploring the potential roles, audiences and challenges of the Facility, its mandate, the management of the Facility defined the Facility’s role and audience for 2014-15 as follows:

The Facility sees its knowledge management role in brokering partnerships and exchanges, and facilitating innovation on the issue of a resilience-based development in context of the Syria crisis. It will do so by also facilitating, investing in and drawing on data-driven catalytic research and development, however, it does not see itself as a research institution.

In terms of audience, it will take an incremental approach over time in which it will – through the work of the Regional UN Working Group on Resilience – focus in the short-term on serving UNDP Country Offices, then expand this work to UNCTs and UNDG agencies, and later target the larger development community of governments, NGOs and other partners.

The incremental approach to widen the audience of the Facility’s work over time is illustrated in the following figure:

Recommended Knowledge Management Activities for the Sub-Regional Facility
One concern raised by the management team of the Facility was that – given the Facility’s limited team size –its KM approach should not be too complex in order to avoid any capacity issues (recruitment of a Knowledge Management Specialist position is planned for Q1 2014). With the direction for knowledge management of the Facility derived from the knowledge needs assessment, and keeping in mind the need for prioritization due to capacity constraints, UNDP was then able to identify potential KM initiatives that can support a knowledge agenda focusing on brokering and innovating – as well as to some extent research – and that targets first UNDP Country Offices and UNDG audiences, as shown in this figure:

The following are the recommendations for knowledge management activities for the Sub-Regional Facility:

An online collaboration space for the Facility, targeted at the Regional Working Group and invited guests;
Establishment of a UNDG-wide Community of Practice on resilience-based development, including selected guests from academia;
Mapping of stakeholders for research on resilience and partners for engagement on Resilience-Based Development;
Exploration of organizing social innovation camps in Jordan, Lebanon and/or Turkey to identify and prototype e-governance solutions for a priority issue (e.g. local services), potentially in combination with a public innovation competition to crowd-source practical solutions to local challenges around resilience-based development.
Series of targeted consultations on questions related to resilience with staff across UNDG agencies, as well as invited external guests from academia, international organizations, NGOs and private sector partners.

While not immediately being in the focus of the Facility in terms of role and audience, the following activities can also add value to its knowledge agenda:

Conducting monthly webinars, to periodically inform UNDP and UNDG stakeholders about the Facility’s ongoing work, outputs and results, and foster learning among stakeholders;
Creation of visualizations and infographics, to use as communication, capacity building and advocacy tool, packaging evidence from research and results of the Facility’s work;
Maintaining a regular blog about the Facility’s ongoing work and results, to increase visibility and influence the general debate on resilience

Finally, to support the Facility’s internal work, the application of the following is also recommended:

Peer Assists, applied as needed to get input from peers on internal tasks and challenges of the Facility;
After-Action Reviews, applied consistently after key events or activities of the Facility to reflect on its ongoing work and capture learning points.

What could those priorities entail in detail? Expect a last blog post elaborating on each of the initiatives, as well as some first results in implementing this work plan!

Figuring out where to begin: How to do KM for a start-up business unit (Part 1)

noreply@blogger.com (Stepping Higher - Reflections on the Knowledge Age) — Wed, 15 Jan 2014 09:01:00 +0000

How do you do knowledge management (KM) when you’re a start up? When the identity of your business unit is still in the making? And when you’re not sure what KM has to offer for what you want to achieve? You bring in someone to help set up the unit, define your role in terms of KM and explain the KM options you have. That’s what the Head of the Sub-Regional Response Facility for Syria in Amman did, requesting a KM expert from headquarters who can assist them in this task on short notice (like, the following week?), and I raised my hand… In reality, it still took about six weeks until I received the call for deployment end of November.

To give some context: Three years into the Syria crisis, the civil war has wreaked havoc in the country, killing over 125,000 people and leading to 2.3 million refugees in Egypt, Iraq, Jordan, Lebanon, Turkey and North Africa, putting a heavy strain of those countries’ public services, employment situation and social cohesion among the host communities. In addition to the refugees, over 6.5 million of the Syrian population is internally displaced (Source: http://www.usaid.gov/crisis/syria), receiving limited services from the international community. Estimates indicate that this is the largest movement of people since the Second World War. In order to respond to this situation that is threatening to reverse development gains of decades in the region, UNDP has decided to establish a Sub-Regional Response Facility to support Country Offices and partners in the sub-region in developing a resilience-based development response to the crisis that goes beyond emergency assistance.

Arriving here in Amman end of November with the prospect of a two-three months detail assignment, my TORs consisted basically of a generic list of all the potential things that KM people can do. The mandate of the Facility had been established two months earlier through a concept note, which mentioned the need for “a strong knowledge management capacity to effectively adapt, align and transform responses to the volatility of the situation… [requiring] …innovation and a strong capacity to learn from errors and successes”, but it didn’t really elaborate how such a function should look like.

So the first goal was to identify the priorities for the Facility in terms of KM. Well, how do go about it? I convened the team and conducted a KM needs analysis in which I asked them “Among the different roles that Sub-Regional Facility could play in terms of knowledge management, what role should it play?”

What are those potential roles? For a newly established entity which wants to position itself among existing partners as a coordinating body, as well as driving force for a specific issue, there are multiple ways how it could interpret its KM work. It could…

Capture Knowledge: Collect data, evidence and lessons from past initiatives to take stock and understand what worked and what didn’t.
Broker Knowledge Exchange: Connect individuals, teams and institutions and facilitate exchanges for mutual learning, support and partnership building.
Do Research: Undertake quantitative and qualitative analysis based on existing or new data to generate evidence, consolidate existing knowledge and generate new knowledge.
Innovate: Identify, sponsor and prototype new potential solutions for complex challenges and questions that haven’t been solved before.
Disseminate Knowledge: Establish channels of communication and training to deliver existing knowledge to target audiences in order to educate, build capacity and raise awareness.

Second, I asked them who they want to do this for? Who is their audience? On a broad level the Facility could distinguish between five layers of target groups:

The Facility itself (KM to increase internal efficiency)
The Regional UNDG Working Group on Resilience
UN Country Teams and UNDG agencies
Governments, IOs, NGOs, Academia, Private Sector
The Public

To give the team some visual aid I put together the following illustration as an overview over the different directions that KM could take for the Facility, and how each role can be played for various layers of target audiences:

For each role and audience, the practice of KM can draw on a range of tools and methodologies. To understand the spectrum of tools and methodologies available, one could skim through the Knowledge Sharing Toolkit (maintained the KM4Dev network, FAO, UNICEF, UNDP and CGIAR) which lists 64 tools and 124 general approaches. For the sake of this exercise, I focused on those tools that UNDP has most experience in, as well as the capacity to support, each of which would require a further look at intent, content and audience:

Knowledge Fairs to identify & reward successful projects or insightful failures, learn from them and scale up (On what topic? With which stakeholders?)
Knowledge Systematization and Transfer Exercises to document lessons and tools from past experiences (On which projects? On which topics? With which partners?)
Communities of Practice for individuals to exchange knowledge and learn from each other (On what topic? For which stakeholders?)
National Solution Exchange Networks to facilitate exchange among development stakeholders in a country (Which country? On what topic? Which stakeholders?)
Knowledge Mapping to identify key stakeholders for knowledge partnerships, exchange and engagement (For what KM activity?)
Online Idea Market to collect new ideas from selected audiences (For which audience? What mechanisms for follow up?)
Public Dialogues or Consultations with targeted stakeholders (To get input on what questions?)
Innovation Challenges/Competitions to identify innovative ideas to complex challenges (On which challenges?)
Crowd Sourcing to identify priorities and concerns of populations (On which issues?)
Social Innovation Camps to identify/prototype new ideas (With which stakeholders? On which challenges?)
Online Collaboration Spaces to host discussions and provide knowledge resources (For which audience? For what purpose? Under which brand?)
Visualizations and Infographics to illustrate research data and communicate results (What story to tell? What data source?)
Webinars to share experiences (Which projects? Which audience?)
Trainings to deliver known content (What content? What audience?)
Public Website to disseminate knowledge resources (What content? What audience?)
Social Media to reach out to the public and raise awareness (What message? What audience?)
After Action Reviews for the Facility to learn from its activities (On which activities of the facility?)
Peer Assists for the Facility to get input from peers on its upcoming tasks (What problem are you trying to solve? Who can assist?)

Each of the tools and methodologies can provide particular value for specific audiences and purposes:

So how did the Facility position itself in terms of priorities for knowledge management? And which KM initiatives did I recommend as a result? You will find out soon in my next blog post update from Amman! :)

Seven guiding principles for knowledge management in your organization

noreply@blogger.com (Stepping Higher - Reflections on the Knowledge Age) — Tue, 10 Sep 2013 17:58:00 +0000

As my organization is currently in the process of formulating a new Knowledge Management Strategy (replacing its past Knowledge Strategy 2009-2011), I recently found myself discussing a lot with colleagues within and outside the organization on what should be key principles or guiding points for knowledge management. I was particularly inspired by colleagues from IFAD which is currently also writing a KM framework, and I found lot of elements that seem to be quite universal across organizations. It seems that regardless of the strategic direction a specific organization might take, and regardless of how KM might relate to their organizational goals, there are a number of principles that ring true to KM practitioners all around. I am listing them here, looking forward to hear whether others can relate:

Most of an organization's knowledge is tacit, stored in the minds of its employees and consultants. Only a part of this tacit knowledge can be documented and made available in information systems. Therefore, KM always needs to be people-centered rather than document-centered, with processes and technology being supportive functions.
Knowledge is most effectively assimilated when shared within a specific context, where the situational variables that were present when a lesson was learned are known, and the context in which certain knowledge might be valuable is clear.
In organizations that don’t offer standardized products, but rather customized and innovative services, knowledge is most effectively shared when an experience can be attributed to the person who made the experience, and where opportunities are available for follow-up discourse and adaptation of the experience to a given problem. This is known as the personalization approach to KM, versus a codification approach.
Knowledge is most effectively shared when there is an audience that is listening, that gives the sharer an idea how the shared knowledge can have a positive impact, and that gives the sharer tangible recognition for his/her act of sharing.
The Cynefin framework provides a typology of four different contexts in which different knowledge solutions might apply: Simple, in which the relationship between cause and effect is obvious to all; Complicated, in which the relationship between cause and effect requires analysis or expert knowledge; Complex, in which the relationship between cause and effect can only be perceived in retrospect; and Chaotic, in which there is no discernible relationship between cause and effect. When developing KM solutions it is crucial to understand the context we are in, as different KM tools only work in specific domains above.
For an organization that must drive complex transformative changes in developing contexts, KM cannot be seen as an additional activity carried out on top of managing development projects, but rather as an activity that is the core value proposition for the organization, and thus as a key contribution to programme delivery, not a stand-alone activity.
While there are valid management rationales for top-down KM initiatives, there will be no value of KM for management (e.g. for results management or donor reporting) if there is not first a value of KM for practitioners, who make experiences and hold tacit knowledge, and who need a rationale to share this knowledge that answers their question “What is in it for me?”.

What do you think about these principles above? Do they resonate with your own experience? Are there additional ones missing? Looking forward to hearing from others on this!

Exit interviews, knowledge databases and other attempts to trap sun rays in a glass jar

noreply@blogger.com (Stepping Higher - Reflections on the Knowledge Age) — Mon, 29 Apr 2013 14:07:00 +0000

This month, I was asked how organizations could introduce a standard process by which all colleagues leaving their job will be requested to document their knowledge, including tools and documents they developed, in a database, so it can be accessed and researched by all colleagues for further reference.

I feel the notion of “capturing knowledge in databases” keeps coming up from time to time like a haunting ghost that you never really get rid of. It important to take it seriously, because it is often a reflection of a deeper misconception in organizations of how knowledge sharing dynamics work, and therefore what knowledge management can (and cannot) achieve.

The truth is that exit interviews and so-called “knowledge databases” are probably among the worst tools one can turn to when choosing a knowledge management approach. To me they are akin to the attempt of trapping sun rays in a glass jar. Let’s look a bit closer at the dynamics that are at play:

While exit interviews and handover notes are indeed established items in the canon of known KM tools, their track record in KM practice has been rather poor. The reason for this, I believe, is that any attempt to “record” knowledge in documents in case someone else might need it in the future, is bound to fail on two fronts:

There is no incentive for the person tasked with recording to do so. People are most motivated to share knowledge

if they get feedback that helps them to learn more, if they receive recognition for their expertise and support; and
if they see a direct impact of what their knowledge contributes to.

None of these incentives are present in the “end of job“ situation. Hence, the maximum we usually get out of leaving staff is a brief handover note that gives an overview over the most critical follow up items and ongoing processes along with necessary next steps, contacts, and maybe an archive folder with all important documents (and getting that is already a success)

Any knowledge captured in documents and databases is just a snapshot, and will both lack context and become increasingly irrelevant with every month that goes by. Databases work well for historical statistical records of past transactions or for policies which don’t change much over time. But for contextual knowledge on how to do things best in different situations, databases don’t work. Because first, they lack the context of the situation a particular experience was made in, and second, they are detached from the actual person making the experience (databases in their nature focus on data and records, not on the people that collect them and have the actual knowledge).

It is for the reasons above that KM in the last 12 years has moved away from attempts to record explicit knowledge in databases for potential future occasions. Instead, the goal has shifted towards fostering continuous interactions between people, as a way to enable just-in-time and in-context interactions. KM’s good track record in facilitating Communities of Practices in which individuals ask questions when they occur, and receive responses from individuals just-in-time and adapted to a given context, is a reflection of this approach. The social media wave since 2006 has taken this even a step further by putting social interactions among colleagues at the center of the knowledge sharing and capturing process. What public and corporate social media platforms (even though they are technically also a databases) are capturing are not mere data records that were uploaded just in case someone needs them, but records of people’s interactions where someone shared something because it was important at that particular time. That record is then indeed searchable and can become a knowledge archive over time. But this cannot be achieved by mandating a staff member to sit down at the end of their assignment and document all they know. Instead, this only works if the staff member engaged throughout his/her assignment in a process of sharing, exchanging and discussion knowledge with peers throughout the assignment.

The situation where knowledge capture does indeed make sense is in context of specific projects or initiatives. There are several standard KM processes to do this, two of which stand out for me:

1. After Action Review: This well-known KM method is applied at certain milestones during and at the end of a project or activity. Participants are being asked four questions: “What was supposed to happen?”, “What did actually happen?”, “Why was there a difference?” and “What can we learn from this for the next project?” It’s a rather informal and brief exercise (anything between 20 min and ½ day) that allows people involved in an activity to step back, reflect, and adjust their action for the next step

2. Knowledge Systematization: This is a more elaborate process (which can sometimes be a project in itself) in which a key project is selected that suitable to serve as a template for how to do similar projects. Through a series of facilitated workshops and reflection exercises, the end goal of this process is to produce a number products that capture the best practices, lessons, tools and template that can be derived from the project, and that can be used to inform similar projects in the future.

It is important to note that both these processes for knowledge capture focus not on a particular staff member, but rather on a specific project/initiative/activity, and the entire team involved in it. They rely on action to be taken during and at the end of a project, not at the end of an individual staff member’s assignment. However, if you have a key project that the leaving staff member was involved with, it might be a good idea to arrange for a knowledge systematization process while that staff member is still in the organization, as s/he will obviously be able to contribute a lot of insights that might otherwise be lost forever.

In addition to the two methodologies above the following action points might be a way forward for someone posing the original question raised in the beginning:

Rather than asking, “What do we need to extract from the departing staff member that the successor needs to know?” we can just ask “What do newly joining team members with a particular function need to know?”. We can create a briefing packages that help with onboarding new staff members, to which all team members add important pieces, standards, templates, tools, processes and resources. This could be the first piece that anyone joining a team should read.
We can try nurturing a blogging culture in our offices, encouraging senior as well as junior staff to formulate their current work, their thoughts on a topic or a recap of a recent event/workshop/training in the form of short and informal blog posts. A group of practitioners on a particular topic can be encouraged to “work out loud”, and in the process will create an environment of discussion, opportunities, learning and innovation.
Back-to-office-reports and debriefings can be done in the form of easy-to-read blog posts, rather than dry and cumbersome forms and reports.
We can introduce regular brown-bag lunches for learning, in which staff present an issue/project/training/process/skill they know about to their peers.
We can virtual spaces for peer-to-peer teams and larger communities on specific issues important to your office (and beyond). Those usually need someone to lead and facilitate them, to support the participants with resources and follow up for discussions. This is also a great opportunity to keep former staff engaged, by giving them access to these dedicated spaces beyond their assignment.
We can try hooking staff in our office up with staff of other offices who have similar issues. This can happen through mentoring approaches at any point in an assignment, and by cultivating staff’s participation in regional and global networks where they can get help on their questions from peers in the organization.

What’s important to keep in mind is that whatever knowledge management mechanism we try to apply, we need to be able to answer the question “what’s in it for me” for those who are supposed to use the mechanism. Policies themselves don’t work. Staff need to have a reason to participate voluntarily (seeing leaders championing an approach, receiving recognition for oneself, getting access to learning opportunities, etc.).

A nice list to find myself on: The world's top 100 global influencers in knowledge management

noreply@blogger.com (Stepping Higher - Reflections on the Knowledge Age) — Fri, 12 Apr 2013 17:36:00 +0000

Very happy to find my name as #75 on the list of the world's top 100 global influencers in knowledge management! Even nicer to see that I am joined (and in most cases precluded) by a lot of dear fellow colleagues from the international development sector, in particular from the KM4Dev network (the Twitter account of which is itself at position #27). Waving in particular to my UN colleagues @ithorpe (#12), @gaurisalokhe (#15), @rsamii (#40) and @johanlammers (#45), as well as other friends in the development community who feature prominently on the list and from the professional insights and colleagueship of which I benefit tremendously.

The list has been compiled and published by the Mindtouch Blog, which frequently features lists of top influencers of different business areas based on a particular Twitter hashtag (in this case #KM). You can access the full list of the top 100 influencers for #KM here.

Ten PowerPoint Slides on Knowledge Management that Have Influenced Me (Part 2)

noreply@blogger.com (Stepping Higher - Reflections on the Knowledge Age) — Thu, 20 Dec 2012 16:57:00 +0000

To get to Part 1 of this blog post, click here.

Do you hate PowerPoint presentations? Well, you probably have endured a lot of gruesome slides throughout the course of your professional life. But despite the usual wisdom that PowerPoint slides for presentations should be avoided whenever possible, I actually think that some well-crafted slides presented in the right context can be a very good thing. In fact, there are a number of slides that had a very positive impact on me in my knowledge management career. I treasure them because they manage to bring complex concepts to the point and often communicate an entire lesson’s worth of insight just with one diagram, graph or image. Here’s a list of ten powerful slides on knowledge management that have influenced me, which I am posting in two parts (for Part 1 click here). See for yourself whether you can get some inspiration from them.

6. The Innovation Adoption Curve

The innovation adoption curve by sociology professor Everett Rogers is a model that distinguishes between different types of adopters of innovations, based on the idea that certain individuals are more open to adaptation than others. Rogers innovation adoption curve is useful to acknowledge that trying to quickly convince all members of an organization of a new controversial idea is useless. Instead it makes more sense to start with winning over innovators and early adopters first. Also the categories and percentages can be used as a basis for setting expectations with senior management and estimating target groups for communication messages. Needless to say that when we introduced corporate social networking in our organization, the adoption pattern looked exactly like the above.

7. Managing Complex Change

This was part of a presentation given by Linda Stoddart from Haute Ecole de Gestion in Geneva during UNSSC’s Knowledge Management course “Think UN, Act Smart”. It’s like a light bulb being switched on when you suddenly realize why you always felt in a certain way when trying to promote KM in your organization, and what conditions need to come together to make complex change happen.

8. Towards a Knowledge Age

Now this is the only slide among this selection that I have created myself. For all its flaws (e.g. that it looks at history from a Western perspective) it is particularly important to me because it illustrates the massive challenge that we face with regards to managing the amount of knowledge that humankind is producing. In addition, it also acknowledges the fact that one of the main drivers underlying this monumental change towards a knowledge society is technology. This is important, as in particular in the KM for Development sphere there is often a dismissive view of technology as mere "tools” that should just follow user needs, while disregarding the fact that it is often technology itself that is creating user needs in the first place and therefore is triggering and reinforcing culture change.

9. RSS in Plain English

These slides are part of a PowerPoint adaption of the video “RSS in Plain English”, and I’m featuring them here as a tribute to the fantastic work that the CommonCraft blog does in producing simple and easily understandable instructional videos on different topics (of which it is the ‘technology’ and ‘social media’ videos that I benefited from the most). Anyone struggling with communicating difficult topics in a presentation can learn a lot from the methodology of the “In Plain English” video series. And it also illustrates that the main key to success in doing a presentation (yes, you can do something similar even with PowerPoint) is telling a convincing story.

10. Shift Happens – Did you know?

This is a quite a famous presentation that has been floating around since 2007 in different versions. It originated from a presentation that Karl Fisch gave to a group of education professionals, and since then has been revised and turned into a video (still based on PowerPoint slides) by Scott McLeod and the company XPLANE. Despite its somewhat sensational tone it serves as an excellent teaser to discuss the changes we are going through as a society and the implications this has for our learning. I usually use a few selected lines and numbers of the presentation when I do training on knowledge management, to set the stage for explaining why we need to deal with KM in the first place. The latest version of the presentation can be viewed as Youtube video here, and older versions are available in the ShiftHappens Wiki.