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

BenchMIRT: What are LLM benchmarks actually measuring?

09.01

BenchMIRT is a new method for auditing LLM benchmarks question by question, revealing which capabilities they actually measure and helping researchers build smaller, more focused, and…

Research

Read at Ai2 ↗

One letter a week, starting soon.

Latest

BenchMIRT: What are LLM benchmarks actually measuring?

Related

LabsHow a Georgia Tech team used the open Olmo stack to trace social reasoning Ai2

LabsTutorMoments: Do AI tutors know when to help and when to hold back? Ai2

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

ResearchWhen LLM judges agree, should we believe them? Amazon Science

ResearchSOP-Bench: A new benchmark for evaluating AI agents on real business procedures Amazon Science

EuropeChoosing a translation API? Read this first DeepL Blog