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

Cline BlogTools

DeepSeek wins IMO Gold on 12 cents

08.26

We wanted to know the cheapest possible way to win an IMO gold medal, so we ran eight models against IMO 2026 problems in Cline and had the proofs graded blind. The answer was 12 cents .

Models & releases

Read at Cline Blog ↗

One letter a week, starting soon.

Latest

DeepSeek wins IMO Gold on 12 cents

Related

ToolsOpen-sourcing evals for open-weight agents Cline Blog

ToolsTop 5 Open Weight Models That Matter to Developers in 2026 Cline Blog

LabsIntelligent transcription with Gemini 3.5 Transcribe Google DeepMind

VoicesHow Claude Watermarks AI-Generated Text Ahead of AI

ToolsGPT-5.6 Sol: Now even cheaper in Devin Cognition (Devin & Windsurf)

ToolsGLM-5.3 vs. GPT-5.6 Sol on DeepSWE: Cost, Coding, and Routing Together AI