Should you engage in "Evals Driven Development"? Probably Not! I bet you thought I would tell everyone to evals max 😆. You have to be reasonable here.

In my experience it's ability to play. Whether you're able to set aside your preconceived notions of it as a fancy toaster and actually give in to the whimsy.

Claude Code 1.0.86 has a new /context command to visualize your context window and token usage It doesn't seem to be accurate yet compared to the auto-compact notice, ccusage, or my status line, but it also shows MCP tool use and CLAUDE.⁠md memory files so could be v useful!

A conversation with cat on: - some tips for using Claude Code - how we prototype new features - customizing Claude Code - how we think about the Claude Code SDK and agents

companies like Facebook record every imaginable interaction their users have with the platform. they log each of your clicks and taps. they keep track of how long your gaze lingered on a post, whether you were on the same WiFi as that woman who might be your friend, which

I want to love Bluesky. The technology behind it is so cool. I like decentralization and giving users ownership over their own data. But then you'll do stuff like talk about running open source AI models at home and get bomb threats.

Continuing the journey of optimal LLM-assisted coding experience. In particular, I find that instead of narrowing in on a perfect one thing my usage is increasingly diversifying across a few workflows that I "stitch up" the pros/cons of: Personally the bread & butter (~75%?) of

great read!

seeing this more in Claude Code and in claude.ai too ☹️

This collection is a treasure: lesswrong.com/posts/SXJGSPeQ… Learning from watching people actually DO things beats abstract instruction every time. More real, more grounded, more concrete. The gap between 'knowing about' and 'knowing how' is massive.

after leading a few projects, i've found that once you've set up the evals + experiment harness and make it easy to tweak config and prompts with 1-click run + eval, teams enjoy running experiments and hill climbing those numbers, and progress comes quickly. but setting up that

ChatGPT Deep Research just ran for 3 hours - longest I've ever seen it go

oh boy, here we go

dirceu how?