I'd Rather Be Writing, by Tom Johnson

Reflections on Ai4 conference - some absences from a tech writer's POV

Sun, 09 Aug 2026 00:00:00 -0700

This week I attended Ai4, promoted as the largest AI conference in North America. It was held at The Venetian in Las Vegas and lasted 3 days. The conference had more than 12,000 attendees (from 100 countries), 400 exhibitors/sponsors, 1,000 speakers, 700 sessions, keynotes from luminaries, and more. Needless to say, the sheer size of the conference was overwhelming. In this post, I'll share thoughts about the conference, focusing on a few key things:

The overwhelming size of the conference
The focus on agents and near absence of skills talk
The absence of any vendors tackling tech comm solutions
Whether conferences are good places to learn

Orchestrating docs instead of writing them yourself — podcast with Sarah Deaton of Anthropic

Sun, 02 Aug 2026 00:00:00 -0700

In this podcast, co-host Fabrizio Ferri-Benedetti and I chat with Sarah Deaton, a technical writer at Anthropic who works on the Claude Code docs, about what documentation work looks like when much of it is automated. We discuss orchestrating docs through skills and agents rather than writing them, mining AI assistant conversations for doc gaps, running forensics on every false claim that reaches the docs, new metrics like time-to-correction and steers per PR, the fences that keep AI-generated docs honest, and how she closed more than a hundred pull requests in a single day.

Building out a course on agent skills

Tue, 21 Jul 2026 00:00:00 -0700

I'm trying to build out a course on agent skills. For a while I've been looking for something more substantial and stable to sink my teeth into (similar to what I did with API documentation), and I think agent skills just might be it.

The gap between academic and industry technical writing: What it is, why it exists, why it's important, and what we can do about it (Part II)

Sun, 12 Jul 2026 00:00:00 -0700

This is Part II of a guest post from Jeremy Rosselot-Merritt, an assistant professor at James Madison University. In this post, Jeremy transitions from describing the reasons for the gap between academics and practitioners (explained in Part I) to solutions. Some solutions involve increasing the conversations between academics and industry professionals, collaborating more with workplace research, having industry professionals guest speak in academic programs, teaching academics what research methodology is acceptable in the workplace, and more.

The gap between academic and industry technical writing: What it is, why it exists, why it's important, and what we can do about it (Part I)

Sun, 12 Jul 2026 00:00:00 -0700

This is a guest post from Jeremy Rosselot-Merritt, an assistant professor in the School of Writing, Rhetoric, and Technical Communication at James Madison University. In this post, Jeremy explains why there's such a gap between industry practitioners and academics. He lays out the case with everything from language, cadence, pressures, motivations, job cycles, promotions, and more, in as clear and straightforward way as possible. This is part I of II.

Tom's opinionated guide to skill building 101

Tue, 30 Jun 2026 00:00:00 -0700

The thing I'm most excited about with AI lately is SKILLs. (I have to capitalize the word at first so you know I'm talking about agent skills rather than just general capabilities; however, I'll subsequently just refer to agent skills as skills.) I've now built about 10 skills for various purposes, and I'd like to write a post that shares some of my thoughts around skill building in a more opinionated way.

AI Book Club discussion of The Infinity Machine by Sebastian Mallaby

Sun, 28 Jun 2026 00:00:00 -0700

This is a recording of the AI Book Club discussion of Sebastian Mallaby's The Infinity Machine: Demis Hassabis, DeepMind, and the Quest for Superintelligence. In the discussion, we talk about the complex character of Demis Hassabis (and comparisons to Ender's game), the idea of founders' personal morality acting as a final safeguard, and the relentless acceleration of AI development. We also talk about the historical rivalries between deep learning and reinforcement learning, the growing urgency around AI-driven job displacement, and what it means to train AI to automate our own work.

Judging beautiful docs, AI fatigue, and tool slop -- podcast with Fabrizio

Sun, 31 May 2026 00:00:00 -0700

In this podcast, I chat with Fabrizio Ferri-Benedetti about a variety of topics related to AI and docs, such as applying Italo Calvino's literary principles of lightness and quickness to evaluate docs, the reality of AI review fatigue versus creator fatigue, whether vibe-coded tools are tools slop, developing internal skills for repeatable doc processes, and the utility of running local AI models.

Review of Max Tegmark's 'Life 3.0: Being Human in the Age of Artificial Intelligence'

Sun, 17 May 2026 00:00:00 -0700

This post is my review of Max Tegmark's Life 3.0, a book we read in the AI Book Club. Tegmark, an MIT physicist and founder of the Future of Life Institute, says Life 1.0 relies entirely on biological evolution to change its hardware and software, Life 2.0 (humanity) can design its own software (through learning and culture) but is stuck with its evolved hardware, and Life 3.0 is a technological stage where life can design both its software and its physical hardware. Although Tegmark's book was published in 2017 (before ChatGPT), the book's core questions about recursive self-improvement, AI alignment, steering beneficial AI, etc., are still highly relevant today.

AI Book Club discussion recording of 'Life 3.0: Being Human in the Age of Artificial Intelligence', by Max Tegmark

Sun, 17 May 2026 00:00:00 -0700

This is a recording of the AI Book Club discussion of Max Tegmark's Life 3.0: Being Human in the Age of Artificial Intelligence. Our discussion explores Tegmark's visions of superintelligence, the unpredictability of AI goals and subgoals, and how the Asilomar principles fare against the relentless market pressures of today's AI arms race. We also contrast the book's theoretical focus on cosmic energy (and how superintelligence might more efficiently extract energy from matter) with the immediate, tangible threats AI poses to cybersecurity and global financial systems.

Developing internal skills for recurring documentation processes like release notes

Mon, 04 May 2026 00:00:00 -0700

My hypothesis this year around AI was that if I develop some agent skills to speed up repeatable processes, it might clear up my bandwidth and free up time for me to work on non-repeatable doc tasks. It appears to be working.

Looking back at the AI Book Club one year in

Tue, 28 Apr 2026 00:00:00 -0700

On pace and value -- why is moving slow boring?

Mon, 27 Apr 2026 00:00:00 -0700

Frenetic thinking

Sun, 26 Apr 2026 00:00:00 -0700

Work expands to fill the space allotted

Sun, 26 Apr 2026 00:00:00 -0700

Too much coffee?

Fri, 24 Apr 2026 00:00:00 -0700

AI Book Club discussion recording of 'Breakneck: China's Quest to Engineer the Future', by Dan Wang

Thu, 23 Apr 2026 00:00:00 -0700

This is a recording of the AI Book Club discussion of Dan Wang's Breakneck: China's Quest to Engineer the Future. Our discussion tries to tie some of the book's themes to AI (to align with the book club's theme), but only in places where it makes sense. Some topics we discuss include social engineering, electric vehicles, contrasting energy infrastructures and the ability to power AI compute, mass surveillance networks, the differences between America's lawyerly society and China's engineering state. Fortunately, one of the book club members had recently been to China and could share firsthand experiences and impressions of cities like Shenzhen and Beijing. Among many observations, she describes the tech fatigue of everyday life, where everything (even prices at stores) requires you to use an app.

Some thoughts after using AI to help with taxes

Mon, 20 Apr 2026 00:00:00 -0700

After receiving a letter from the IRS stating that I owed more taxes on a previous year, I used AI to identify the issue -- a missing cost basis on stock sales. I then successfully disputed the notice, and ultimately claimed a sizable refund by carrying over capital losses. AI tools like Claude and Gemini have become surprisingly capable at analyzing uploaded tax returns and guiding novices like me through complex scenarios.

Podcast: How valuable are agent skills? Conversation with Larah Vasquez and Fabrizio Ferri-Benedetti

Sun, 12 Apr 2026 00:00:00 -0700

In this podcast, I chat with Larah Vasquez and Fabrizio Ferri-Benedetti about using skills to extend AI capabilities, the future of agentic engineering, local models like Qwen and Gemma, and whether the tech writer role is shifting into automation architecture. We get into the memory problem in LLMs (and why some of us actually prefer the no memory to extended memory), the progression from prompt engineering to context engineering to compound engineering to orchestrating whole agent systems, and how skills are quietly forcing engineers to write down knowledge they'd never documented before.

The Emerging Picture of a Changed Profession: Cyborg Technical Writers — Augmented, Not Replaced, by AI

Sun, 05 Apr 2026 00:00:00 -0700

I recently gave a presentation to students and faculty in person at Louisiana Tech University on March 30, 2026, focusing on what I call the cyborg model of technical writing. The idea is that the emerging model for tech writing isn't one in which AI replaces tech writers but rather one in which AI augments tech writers. Tech writers interact with AI in a continuous back-and-forth, conversational, iterative manner. This post contains the recording, slides, transcript, summary, notes, and more from my presentation.