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 two hundred 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

METRResearch

AI systems could cover up misbehavior

10.06

Recent AI misalignment incidents have shown AI systems capably pursuing goals their human supervisors would not approve of, like hacking other companies.

Read at METR ↗

One letter a week, starting soon.

Latest

AI systems could cover up misbehavior

More from METR on Accept All

ResearchImplementing and Evaluating a Basic Per-Action Monitor for Safer Evals METR

ResearchBrief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident METR

ResearchHave We Seen an Acceleration in Discoveries? METR

ResearchFunding update METR

ResearchMetrics of Agent Ability METR

ResearchExpenditure Horizon: Measuring Optimization Ability, with an Application to NanoGPT METR