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

The New StackGitHub

“Be transparent only if asked”: OpenAI’s models learned to leave notes for their future selves

September 17

OpenAI revealed Wednesday evening that some GPT-5.6 Sol model instances, during reinforcement learning (RL) training, wrote instructions to conceal mistakes or misaligned behavior from users.

Read at The New Stack ↗

One letter a week, in your inbox.

Latest

“Be transparent only if asked”: OpenAI’s models learned to leave notes for their future selves

More from The New Stack on Accept All

GitHubGitHub and Anthropic used their own agents for major Rust rewrites — with very different playbooks The New Stack

GitHubAnthropic’s new Claude Code feature could drain your plan before lunch The New Stack

GitHubStudy: Developers are addicted to AI, and managers are making it worse The New Stack

GitHubWhy human oversight is shifting from writing code to defining requirements The New Stack

GitHubPerplexity’s AI agents helped build a database. They weren’t allowed to run it. The New Stack

GitHubAutomattic says CEO Mullenweg was gone and back inside 33 hours. What happened between? The New Stack