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

AI Alignment ForumResearch

Neural nets are exceptionally vulnerable to goal self-hack

10.21

Suppose we have an AI CEO, ruthlessly devoted to maximising shareholder value. Fortunately, we haven't been completely stupid, and have given it a rich definition of shareholder value, encompassing…

Read at AI Alignment Forum ↗

One letter a week, starting soon.

Latest

Neural nets are exceptionally vulnerable to goal self-hack

More from AI Alignment Forum on Accept All

ResearchA Simpler and Better Debate Protocol for Scalable Oversight AI Alignment Forum

ResearchThe Continual Constitutional Convention: How language models revise the documents that govern them AI Alignment Forum

ResearchRocks to Rules: Climbing a Rickety-But-Interoperable Semantic Ladder AI Alignment Forum