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

olmo-eval: An evaluation workbench for the model development loop

June 12

olmo-eval is an open evaluation workbench that helps model developers add, run, and analyze benchmarks across changing LLM checkpoints, extending OLMES from final-score reproducibility into the…

Research Funding & deals

Read at Ai2 ↗

One letter a week, in your inbox.

Latest

olmo-eval: An evaluation workbench for the model development loop

Related

VoicesOpen-world evaluations for measuring frontier AI capabilities AI Snake Oil

VoicesUnderstanding the 4 Main Approaches to LLM Evaluation (From Scratch) Ahead of AI

VoicesUsing LLM-as-a-Judge For Evaluation: A Complete Guide Hamel Husain

LabsIntroducing AIMIP: The AI weather and climate model intercomparison project Ai2

VoicesLLM Research Papers: The 2026 List (January to May) Ahead of AI

ToolsReinforcement learning is an infrastructure problem Modal