The name is the button.

An agent writes the code now, and a human thumb hovers over Accept all a hundred times a day. The honest question of this decade is what, exactly, you just accepted. So I read the diff.

Eight years as a backend engineer in Stockholm, back in Tokyo since 2023, and I still ship something small most nights, usually badly. My one rule: the only real review of a model is the thing you built with it. That is why there is no leaderboard on this site.

Around a hundred and forty sources come through — the labs' own posts, the papers, the tools, the runtimes and languages nobody is watching yet, the chip under the demo, and the newsletters people actually forward. What is moving gets counted so the week reads at a glance, and every few days I explain one mechanism in plain words.

A story here is a headline, a short excerpt, one image and the link to whoever wrote it. We never reproduce the post; the images belong to their authors. A post written in Japanese appears in Japanese, exactly as it was published, and the link goes to the original.

— Yuki Halvorsen, Tokyo

← Accept All Archive

Ai2Labs

How Goodfire used Ai2’s open post-training stack to trace unwanted model behavior

September 9

Goodfire used Ai2’s fully open post-training stack to predict LLM behavioral changes, trace unwanted model behavior back to individual training examples, and test targeted fixes without sacrificing…

Read at Ai2 ↗

One letter a week, in your inbox.

Latest

How Goodfire used Ai2’s open post-training stack to trace unwanted model behavior

More from Ai2 on Accept All

LabsBenchMIRT: What are LLM benchmarks actually measuring? Ai2

LabsThe hard parts of AI-assisted science Ai2

LabsAi2 and Providence Swedish Cancer Institute partner to advance AI-assisted scientific discovery Ai2

LabsHow researchers adapted Dolma for better Thai language models Ai2

LabsHow a Georgia Tech team used the open Olmo stack to trace social reasoning Ai2

LabsWhen a model reads a drug's class from its name—not its knowledge Ai2