I'm hopeful that work on voice-enabled models will lead to this kind of solution. Streaming is so hard, but it feels like the end-state in the evolution of sophisticated systems.

I think I've learned as much in the last two years (since starting to program with AI assistance) as I did in the first 25 years of my career. This new learning mode is really cool, check it out!

This email should have been a calendar invite.

Don't even build tools, just use the agent to explore the dataset.

We've published a detailed postmortem on three infrastructure bugs that affected Claude between August and early September. In the post, we explain what happened, why it took time to fix, and what we’re changing:

The gen AI era is so fun for the type of programmer who relentlessly tweaks their dev environment. There's so much alpha in experimenting with new workflows right now. This is why I stick to zsh, neovim and tmux. They are easy to automate and Claude knows them inside out.

For some time now, we've been saying "Claude Code is all you need." By this we mean that Claude Code and the SDK which is based on it can power much more than coding. Here's a big step in that direction: making Claude Code fully pluggable. Can't wait to see what you build.

So many interesting ideas here. Just a couple: 1. AI generates disposable simulation code to discover UX issues. Insane speed multiplier vs manual testing. 2. Documentation is a prompting tool. Good docs help the AI work better next time. Compounding returns.

Ok, when I talk about React useEffect being confusing, here's an example: I want to respond to an abortSignal passed as a prop to my component. Is this correct? Is the useEffect necessary? I want to ensure that I never see a stale value for isAborted.

Every agent is a coding agent.