Scottish software developer on the Statamic core team; runs a one-person business maintaining Statamic addons such as Runway and writes at duncanmcclean.com.

• Usesrcmnd.app

  Claude

  Their words

  Claude is currently my main AI tool. I use the Claude desktop app, and Claude Code via Opencode.

  duncanmcclean.com

Technology analyst whose weekly email on tech reaches over 150,000 readers. Publishes essays and an annual presentation on where the industry is going.

From one piece Why Everyone Is Wrong About AI (Including You) | Benedict Evans 2 beliefs, in the piece's order there

• Our readingkorrents.com

  Studies showing a language model behaving badly prove nothing, because the model was asked to produce that behaviour.

  Anthropic

  Their words

  you write murder is good on a piece of paper and you put it in a photocopier and you press go and you say my god the machine says murder's good. Well, no, you told the machine to say that. And that's what these anthropic studies are. They're basically you tell the machine to say a thing and then it says it like well you haven't proved anything.

  youtube.com

• Our readingkorrents.com

  The leading chatbots are undifferentiated: in a blind test most people could not tell one model's output from another's.

  AnthropicGoogle

  Their words

  Like it seems to me right now you could do like a double blind test of the same prompt given to Grock Claude Gemini um Mistral Deep Seek. Do a double blind test. I bet most people wouldn't be able to tell which is which.

  youtube.com

Founded PSPDFKit in 2011 and ran it for a decade. Came back from a break to work on AI agents — the OpenClaw project, and OpenAI, joined in February 2026. Writes at steipete.me.

• Our readingkorrents.com

  MCP servers are worth removing outright: an agent reading the code directly is faster, and pollutes its context less, than one that can reach for a tool unasked.

  MCPAnthropic

  Their words

  Even removed my last MCP, since Claude sometimes would go off spinning up Playwright unasked when it could simply read the code - which is faster and pollutes the context less.

  My Current AI Dev Workflowsteipete.me

Founded PSPDFKit in 2011 and ran it for a decade. Came back from a break to work on AI agents — the OpenClaw project, and OpenAI, joined in February 2026. Writes at steipete.me.

• Lovedrcmnd.app

  Dell UltraSharp U4025QW

  Their words

  3840x1620 makes 4 Claude instances + Chrome all visible without moving windows.

  steipete.me

• Recommendsrcmnd.app

  Claude Code

  Their words

  TL;DR: Ghostty + Claude Code + minimal tooling = maximum productivity.

  steipete.me

Professor at Wharton studying how people actually use AI, and author of Co-Intelligence. Writes One Useful Thing, where the claims are dated and testable because the thing they describe keeps changing under them.

• Recommendsrcmnd.app

  ChatGPT

  Their words

  So, for most people, just stick with Gemini, Claude, or ChatGPT

  oneusefulthing.org

• Recommendsrcmnd.app

  Gemini

  Their words

  So, for most people, just stick with Gemini, Claude, or ChatGPT

  oneusefulthing.org

• Usesrcmnd.app

  OpenAI o3

  Their words

  I use o3, Claude 4 Opus, and Gemini 2.5 Pro for any serious work that I do.

  oneusefulthing.org

Creator of Flask and Jinja. Writes about software at lucumr.pocoo.org.

• Likedrcmnd.app

  Claude Sonnet

  Their words

  I exclusively use the cheaper Sonnet model. It’s perfectly adequate for my needs, and in fact, I prefer its outputs over the more expensive Opus model.

  lucumr.pocoo.org

Co-creator of Django and creator of Datasette; writes daily at simonwillison.net.

• Lovedrcmnd.app

  Anthropic prompt engineering documentation

  Their words

  I still think Anthropic have the best prompting documentation of any LLM provider.

  simonwillison.net

Co-creator of Django and creator of Datasette; writes daily at simonwillison.net.

• Lovedrcmnd.app

  Claude 3.7 Sonnet

  Their words

  As a Python and JavaScript programmer my favorite models right now are Claude 3.7 Sonnet with thinking turned on, OpenAI’s o3-mini-high and GPT-4o with Code Interpreter (for Python).

  simonwillison.net

Machine-learning researcher on open language models; writes the Interconnects newsletter and the RLHF Book, after leading post-training at Ai2.

• Our readingkorrents.com

  Making safety your number one goal costs real release speed, and on a steep progress curve that shows up directly as a worse-looking model.

  AnthropicAmerica

  Their words

  We know that a lot of the American companies are very invested in safety, and that is the central culture of a place like Anthropic. And I think Anthropic sounds like a wonderful place to work, but if safety is your number one goal, it takes way longer to get artifacts out.

  youtube.com

Creator of Flask and Jinja. Writes about software at lucumr.pocoo.org.

• Usesrcmnd.app

  Ollama

  Their words

  First and foremost, I use this to talk to local models hosted by Ollama, but secondarily I also use it to interface with other remote services like OpenAI, Anthropic and DeepSeek.

  lucumr.pocoo.org

Professor at Wharton studying how people actually use AI, and author of Co-Intelligence. Writes One Useful Thing, where the claims are dated and testable because the thing they describe keeps changing under them.

• Lovedrcmnd.app

  Claude 3.5 Sonnet

  Their words

  and really only has one model you care about - Claude 3.5 Sonnet. But Sonnet is very, very good. It often seems to be clever and insightful in ways that the other models are not.

  oneusefulthing.org