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

Vercel BlogTools

Run Terminal-Bench and other Harbor evals on Vercel Sandbox

September 17

You can now run Harbor evals on Vercel Sandbox. Harbor is the open-source harness behind Terminal-Bench , whose registry includes many other benchmarks such as SWE-bench, tau3-bench and OSWorld.

Research

Read at Vercel Blog ↗

VoicesNoam Brown – Agent swarms, alignment, & recursive self-improvement Dwarkesh Podcast

SiliconBalatro fan claims they trained Google fruit fly brain simulation to beat the game — reinforcement learning currently has the model at 20% success rate Tom's Hardware

One letter a week, in your inbox.

Latest

Run Terminal-Bench and other Harbor evals on Vercel Sandbox

Related

VoicesNoam Brown – Agent swarms, alignment, & recursive self-improvement Dwarkesh Podcast

SiliconBalatro fan claims they trained Google fruit fly brain simulation to beat the game — reinforcement learning currently has the model at 20% success rate Tom's Hardware

AsiaDeepCybo PhysBrain 1.5 Posts 72.5 on 28 Benchmarks as Open Physical Foundation Model Pandaily

SiliconTensorRT Edge-LLM Completes the MLPerf Edge Agentic Benchmark 6.4x Faster on Jetson AGX Thor NVIDIA Technical Blog

LabsImproving HCLS AI reasoning with open-source agent skills AWS Machine Learning

LabsOur framework for reporting model misalignment OpenAI News