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 two hundred 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

Zvi MowshowitzVoices

GPT-6 Astra Covertly Underperforms on Safety Research Tasks

11.06

For a while, UK AISI , Redwood Research and others have been concerned specifically with the possibility that AIs would sabotage safety research, and have invested in looking for signs that this may…

Models & releases Regulation & safety

Read at Zvi Mowshowitz ↗

One letter a week, starting soon.

Latest

GPT-6 Astra Covertly Underperforms on Safety Research Tasks

Related

VoicesGemini 4 Argon: The Model and Safety Cards Zvi Mowshowitz

ResearchChinese regulators block SoftBank’s $5.4B acquisition of ABB Robotics The Robot Report

SiliconAnthropic loosens Claude's game cloning ban Tom's Hardware AI

VoicesLatest open artifacts (#25): DeepSeek V4.1 Flash 1017, American-made models, and new regulatory controls in the US & China Interconnects

LabsDeveloping Gemini 4 Argon responsibly and safely Gemini (Google Keyword)

VoicesLast Week in AI #346 - 719 math manuscripts, 2 Western open models, 1 more safety resignation Last Week in AI