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

Redwood ResearchResearch

Screwtape: Adversarial Transcript Editing for Monitor Red-Teaming

10.16

Automatically finding monitor failures by editing real agent transcripts

Read at Redwood Research ↗

One letter a week, starting soon.

Latest

Screwtape: Adversarial Transcript Editing for Monitor Red-Teaming

More from Redwood Research on Accept All

Research[Paper] Distillation for Incrimination and Distillation for Capabilities Redwood Research

ResearchFrontier models state different decision theory preferences depending on who’s asking Redwood Research

ResearchCapabilities research expands the safety-usefulness Pareto frontier too Redwood Research

ResearchContinual learning might make your blocking monitors nearly useless Redwood Research

ResearchLatent reasoning architectures would likely undermine CoT, our strongest oversight tool Redwood Research

ResearchAstra is much better at reasoning with filler tokens than previous models Redwood Research