Today
- 8 Tips for Writing Agent Skills. Know What a Skill Is, Nail the Description, Write Instructions, Keep It Lean, Set the Right Level of Freedom, Don't Skip Negative Cases, Test It Before You Ship It, Know When to Retire a Skill....
- I quipped on BlueSky: It’s interesting how AI proponents are often like "skill issue" when the LLM doesn't work like someone expects. Whereas when human-centered UX people see someone using it wrong, they're like "skill issue on us, the people who made this" This is top of mind...
Yesterday
- April 2026 I’ve been having moderate success using an AI agent to help me fix non-trival bugs in GoAWK. But it’s sometimes very indecisive (Mitchell Hashimoto noted this in a tweet just the other day). I asked it the following question (I’m using Claude’s Opus 4.6 with the...
- Blog About Moonbound Shop This is a post from Robin Sloan’s lab blog & notebook. You can visit the blog’s homepage, or learn more about me. April 12, 2026 Just yesterday discovered the company Tinfoil, which is doing some really cool work with AI models running inside...
- AI coding agents consume documentation fundamentally differently from humans. If you're still optimizing only for human readers, you're leaving a growing share of your audience invisible to your tooling....
This week
- April 10, 2026 The path through the irises, 1914-1917, Claude Monet The new language models are children of the reasoning revolution, and they stream out these long, circuitous thinking traces. They are said to be applying more compute to our questions and challenges....
- Today we're launching the Mastra platform with tools to develop, run, manage and monitor your agents effectively at scale — featuring Mastra Studio, Mastra Serv......
- I mostly link to written material here, but I’ve recently listened to two excellent podcasts that I can recommend. Anyone who regularly reads these fragments knows that I’m a big fan of Simon Willison, his (also very fragmentary) posts have earned a regular spot in my RSS...
- Meta announced Muse Spark today, their first model release since Llama 4 almost exactly a year ago. It’s hosted, not open weights, and the API is currently “a private API …
- Rahul Garg finishes his series on reducing the friction in AI-Assisted Development. He proposes a structured feedback practice that harvests learnings from AI sessions and feeds them back into the team's shared artifacts, turning individual experience into collective...
- Running multiple agents in parallel is not just a question of throughput. It is a new kind of cognitive labor that requires managing multiple mental models, continuous judgment calls, and an ambient anxiety tax...
- Anthropic didn’t release their latest model, Claude Mythos (system card PDF), today. They have instead made it available to a very restricted set of preview partners under their newly announced …
- Mastra Studio now has an Agent Editor that lets subject matter experts and product teams iterate on agent behavior from Studio, without touching code or redeplo......
- April 7, 2026 It’s a small thing, yet it says a lot, that OpenAI’s Industrial Policy for the Intelligence Age is presented only as a PDF that looks terrible, with amateurish justification and a footer image that’s too lo-res and blurry for clear printing. I’ll note also...
- Google's Gemma 4 family of open models is now available through the Gemini API and Google AI Studio. Built from the same research behind Gemini 3, these models bring advanced reasoning, native function calling, multimodal understanding, and 256K context windows to an open,...
- April 6, 2026 A new edition of my pop-up AI newsletter just landed: where is it like to be a language model? The discussion here is bolstered by an actual experiment, a programmatic probe of many language models. It was my first time doing something like that — fun! The...
- Did you know that Jesus gave advice about prototyping with an LLM? Here’s Luke 14:28-30: Suppose one of you wants to build a tower. Won’t you first sit down and estimate the cost to see if you have enough money to complete it? For if you lay the foundation and are not able to...
- With enough work you can build a search system with just grep. But it’s not for the faint of heart....
Last week
- I like reading system prompts, either when they’re published as part of open-source software, exfiltrated via crafty prompting, explicitly shared, or (in the case of last week) accidentally leaked. They’re often the best manual for how an app is intended to work. We’ve touched...
- AI Assisted/Agentic programming are pretty common place at this point. The growing sentiment seems to be that if you can't find some sort of benefit in your workflow, it's more of a skill issue than a problem with the tools. Whether you believe this to...
- You may be seeing posts claiming METR’s widely-cited 2025 study has been followed up with new research showing an 18% productivity boost. That’s not what the article says. METR: We are Changing our Developer Productivity Experiment Design In 2025, METR found experienced...
- Back in 1985, computer scientist Peter Naur wrote “Programming as Theory Building”. According to Naur - and I agree with him - the core output of software engineers is not the program itself, but the theory of how the program works. In other words, the knowledge inside the...
- I have no connection to the authors of the Superpowers plugin for Claude Code, but I have been raving about it to everyone I talk to. Using Claude Code with Superpowers is so much more productive and the features it builds are so much more correct than with stock Claude Code. I...
- I was a guest on Lenny Rachitsky’s podcast, in a new episode titled An AI state of the union: We’ve passed the inflection point, dark factories are coming, and automation …
Rows per page
