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

Tsinghua's SRHarness Helps AI Agents Find Formulas, While MechBench Tests Whether They Grasp Why

October 14

Researchers at the Data Science and Intelligence Lab in Tsinghua University's Department of Electronic Engineering have released two linked pieces of AI for Science work: SRHarness, a runtime…

Agents & vibe coding

Read at Pandaily ↗

One letter a week, starting soon.

Latest

Tsinghua's SRHarness Helps AI Agents Find Formulas, While MechBench Tests Whether They Grasp Why

Related

AsiaOpen-Source WeChatBridge Arrives on Windows in Beta, Sending WeChat Chats to Codex and Other Agents Pandaily

AsiaAlibaba Opens Sign-Ups for Qwen Go!, a Personal Agent That Files Flight-Delay Claims and Refunds Pandaily

AsiaAgentic AI Startup RevRag.AI Nets $2.5 Mn To Build AI Relationship Managers For Lenders And Insurers Inc42

ValleyPluto Security nabs $42M to help enterprises secure their AI agents SiliconANGLE

ValleyIntel bets the next phase of AI belongs to the rightsized system, not the biggest one SiliconANGLE

ValleyScuba launches with $34M to help teams and AI agents manage business data SiliconANGLE