Latest

On the calendar

予定 · Conferences and launch events, this week's stories from each corner of the industry, and what its press is covering — in English

On view

This week, from that corner the newest stories from the corner of the industry you picked

The wire their own posts, translated

How code moves in 2026 from the industry's own reports

Sources

Fetched every three hours, linked to the original

About

Accept All is a magazine, a radar and a diary about artificial intelligence and the craft of code — read from Tokyo, for people who build.

The name is the button. Code is written by agents now and reviewed by a human thumb that hovers over Accept all a hundred times a day; the whole question of this decade is what, exactly, you just accepted. So we read the diff. A magazine, because every week one model, one tool or one idea is worth reading about slowly. A radar, because we count what the labs, the Valley, GitHub and the chip makers are talking about — releases, agents, open weights, compute, funding, rules — and show it as it moves. A diary, because a seal is set each day in that day's colour, and the days add up.

We read the research labs' own posts, the American and European tech press, the Japanese and Chinese developer sites and the newsletters people actually forward, and bring it together in English and Japanese. Everything here links back to the people who wrote it; the images belong to their authors.

Accept All will keep changing. New sources, new signals, new ways of looking — a little better each week, never finished. If something here made you open a terminal, that is enough.

Thank you for reading. ありがとうございます。

← Accept All Archive

AI Alignment ForumResearch

Training on probes: What's going on

September 8

TL;DR If you train a probe for some property (like "honesty") and do gradient descent against this probe while continuing training that incentivizes dishonesty, the model will change its internal representation to evade

Read at AI Alignment Forum ↗

One letter a week, in your inbox.

Latest

Training on probes: What's going on

Related

ResearchTraining on probes: Research ideas AI Alignment Forum

ResearchHow good are slop-vestigators? AI Alignment Forum

ResearchAstra can do a concerning amount with no chain of thought AI Alignment Forum

ResearchAn operationalization of opaque serial depth AI Alignment Forum

ResearchCoT controllability evals seem very under-elicited AI Alignment Forum

ResearchShallow Beliefs: Midtraining does not inoculate against EM from reward hacking AI Alignment Forum