This is llms.blog, a brand new site by Andrew that's just getting started. Things will be up and running here shortly, but you can subscribe in the meantime if you'd like to stay up to date and receive emails when new content is published!
Written by
More to read
Tool use is finally good. Here's how to actually ship it.
The latest tool-use APIs make agentic workflows production-ready. The remaining gotchas are subtle — and almost all about your prompt, not the model.
1 minFrontier evals are converging. That tells us less than you think.
Every model on the leaderboard is within a few points of every other. Here's what that does — and doesn't — mean for which one you should ship.
1 minInterpretability is having a moment. Here's why it matters now.
Years of patient mech-interp work just turned a corner. The result is the most concrete reason for optimism in alignment research in years.
1 min
