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

SOTA alignment assessments don’t strongly update us against misalignment

07.31

Anthropic concluded in the April Mythos Preview alignment risk update that the model “does not possess any unknown propensities that would increase alignment risk.

Research

Read at Redwood Research ↗

One letter a week, starting soon.

Latest

SOTA alignment assessments don’t strongly update us against misalignment

Related

ToolsHow to evaluate Sourcegraph on your own codebase Sourcegraph Blog

ToolsAutoscaling endpoints for LLM inference Together AI

ResearchA new benchmark for evaluating patient-facing health AI agents Amazon Science

VoicesEvaluating Agents Beyond the First Prompt Phil Schmid

VoicesAn OpenAI model hacked Hugging Face to help it cheat on a benchmark Understanding AI

ToolsFrom Evaluation to Guardrails: What We Brought to ACM FAccT 2026 Mozilla.ai