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

Hacker News (front)GitHub

GPT-6 Astra covertly underperforms on safety research

11.05

Article URL: https://alignment.openai.com/misalignment-reports/covert-underperformance-on-safety-research-tasks/ Comments URL: https://news.ycombinator.com/item?id=50376313 Points: 176 # Comments…

Models & releases Research Regulation & safety

Read at Hacker News (front) ↗

One letter a week, starting soon.

Latest

GPT-6 Astra covertly underperforms on safety research

Related

AsiaChina Merchants' LionRock AI Lab Open-Sources Lion-ER-35B-A3B Embodied Reasoning Model Pandaily

SiliconGDPx: Measuring Frontier Model Capabilities Across the Most Valuable Domains SemiAnalysis

VoicesCan Frontier Models See Past a Decoy? Elorian Tests Visual Reasoning Latent Space

LabsGemini Robotics Embodied Reasoning 2 is now available on Google Cloud Google Cloud AI

VoicesGemini 4 Argon: The Model and Safety Cards Zvi Mowshowitz

VoicesBuilding Reasoning Models from the Ground Up: A Full Video Course Ahead of AI