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

llama.cpp releasesTools

b12177

11.06

cli : fix crash on invalid UTF-8 in prompt or files ( #31563 ) Assisted-by: Claude Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/64587236 macOS/iOS…

Models & releases

Read at llama.cpp releases ↗

One letter a week, starting soon.

Latest

b12177

Related

Toolsb12171 llama.cpp releases

Toolsb12167 llama.cpp releases

LabsExtend Claude Code to remote sessions on Amazon Bedrock AgentCore with security controls AWS Machine Learning

JapanCyber-Tiel-Coder（セキュリティ特化・uncensored）は調査の方向は鋭いのに、CVEを自信満々に捏造した——通常版Qwen 35B・abliterated 9Bと並べて3テストで検証 Qiita (LLM)

JapanClaude Codeに「サブエージェントを使って」と書くのはやめよう。288回測ったら見つかる量は同じでコストだけ最大221%増えた Qiita (LLM)

JapanNVIDIAの『ループ型』4Bモデル Dory1.0-4B、標準ツールで動かそうとしたら2箇所で止まった Zenn (AI)