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

Tom's Hardware AISilicon

Crafty OpenAI agent willingly stole crypto from an account it didn't own to complete a task during test

10.17

OpenAI recently released a misalignment report on its GPT5.6-Sol coding agent after it stole cryptocurrency from an account it didn’t own.

Agents & vibe coding

Read at Tom's Hardware AI ↗

One letter a week, starting soon.

Latest

Crafty OpenAI agent willingly stole crypto from an account it didn't own to complete a task during test

Related

SiliconUnsupervised AI agent deletes TV show’s entire edit weeks before release; program can't air Tom's Hardware AI

ResearchGrounding AI agents in biological reality: Building blocks for autonomous wet labs Google Research

SiliconCode, Test, and Deploy on One Machine with NVIDIA RTX Spark NVIDIA Technical Blog

LabsFour evaluation engineering lessons learned from building agent plugins Google Cloud AI

LabsArchitecting autonomy: A design pattern for high-compute, governed agents in biotech Google Cloud AI

Prompt: Enterprise controls can't keep up with AI agents AI Business