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

Hacker News (front)GitHub

LFM2.5-24B-A2B: Built for fast on-device agents

October 14

Article URL: https://www.liquid.ai/blog/lfm2-5-24b-a2b Comments URL: https://news.ycombinator.com/item?id=50097369 Points: 211 # Comments: 44

Models & releases Agents & vibe coding Open weights

Read at Hacker News (front) ↗

One letter a week, starting soon.

Latest

LFM2.5-24B-A2B: Built for fast on-device agents

Related

LabsRun fast, private agents on-device with LFM2.5-24B-A2B Hugging Face Blog

ToolsOpen-sourcing evals for open-weight agents Cline Blog

GitHubLinus Torvalds let Claude Code fix the Linux page cache. Then reviewers found a race. The New Stack

ValleyGroundcover lets Claude and Codex hand production investigations to its own agent SiliconANGLE

GitHubGoogle Antigravity SDK Adds Local Model Support for Greater Token Efficiency and Code Privacy InfoQ AI

AsiaModelBest Open-Sources MiniCPM-V 4.7, Its First MoE Multimodal Model, Running in 3GB on a Phone Pandaily