Mame Mutually Assured Ai Malfunction Paper By Dan Hendrycks Alex Wang Eric Schmidt
1 mentions across 1 person
All mentions
“The main paper was really interesting. Basically for folks who didn't read it they had a few different things in there but the key idea this MAME idea I think was like mutually assured AI malfunction”
AI Governance Requires Adaptation Buffers, Not Nonproliferation: Helen Toner on ↗