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

PandailyAsia

Meituan Releases LongCat-2.5, a 1.6T Native Multimodal Model Built for Long-Horizon Agentic Coding

11.02

Meituan's LongCat team released LongCat-2.5 on November 2, a native multimodal model built for long-horizon agent tasks, IT Home reported.

Models & releases Agents & vibe coding

Read at Pandaily ↗

One letter a week, starting soon.

Latest

Meituan Releases LongCat-2.5, a 1.6T Native Multimodal Model Built for Long-Horizon Agentic Coding

Related

AsiaDeepSeek Harness Team Open-Sources a Super-agent Prototype That Finds and Fixes Bugs on Its Own Pandaily

AsiaDeepSeek unveils AI ‘super agent’ in coding race with OpenAI, Anthropic SCMP Tech

SiliconAI agent used to perform controversial brain surgery on a mouse, Anthropic Sonnet controlled motorized surgery rig Tom's Hardware AI

ValleyHow a Contractor’s Claude Agent Got Into the Pentagon Wired AI

VoicesMistral Large 4 OSS 🧠, agent swarm behavior 🤖, Sam Altman interview 🍺f TLDR AI

GitHubAnthropic Says Nobody Needs a Mental Model of Claude Code. Practitioners Are Testing That InfoQ AI