The letter

One letter a week, in your inbox.

The week's signal, what shipped, what is worth running tonight, 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

A Defense of Gradual Disempowerment

September 17

(Or: Why Bentham's Bulldog and John Halstead are wrong in their critique of Kulveit et al. ) Gradual Disempowerment is a 2025 paper (with a nice, dedicated website ) proposing a form of existential…

Read at AI Alignment Forum ↗

More from AI Alignment Forum on Accept All

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

ResearchOp-Ed: I Worked at Google DeepMind. You Should Listen to the Warnings About AI AI Alignment Forum

ResearchCoT controllability evals seem very under-elicited AI Alignment Forum

ResearchAn operationalization of opaque serial depth AI Alignment Forum

ResearchProposal for tracking the effects of architecture on monitorability AI Alignment Forum

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

More from AI Alignment Forum on Accept All.