The letter

One letter a week, in your inbox.

The signal of the week, what shipped, what to try, and the editor's note. No tracking, no ads, nothing else.

We keep your address, your language and the date you joined, nothing else. Every letter has a one-click unsubscribe link that deletes the record.

← Accept All   Archive
AI Alignment ForumResearch

Exploration Hacking in AI Debate: Initial Empirics and Generalisation Splitting

September 8

This is the first of two posts resulting from a recent Astra/MATS research project investigating exploration hacking in AI debate.

Read at AI Alignment Forum ↗

More from AI Alignment Forum on Accept All

More from AI Alignment Forum on Accept All.