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

Summary of METR's predeployment evaluation of Claude Opus 5.5

09.22

Note on independence: This evaluation was conducted under an unpaid agreement for AI R&D assessment. 1 We drafted the initial summary, and then Anthropic had the opportunity to review and edit the…

Models & releases Research Funding & deals

Read at METR ↗

One letter a week, starting soon.

Latest

Summary of METR's predeployment evaluation of Claude Opus 5.5

Related

ToolsBenchmarking Local LLM Servers: llama.cpp, llamafile, LM Studio, and Ollama Mozilla.ai

VoicesGPT-6 Astra, Looped Transformers, and Hidden Reasoning Ahead of AI

EuropeMistral raises €3B to make sovereign, open-weight AI the technology frontier Mistral AI

ToolsNvidia reportedly agrees to purchase Hugging Face for $13B Weights & Biases

LabsPiloting the world's first double-blind AI evaluations Google DeepMind

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