It is possible to verify the formal claims of an untrustworthy superintelligence by usinga proof-checker that has been verified by hand, such as https://t.co/rL8eEE3MPh,compiled using a compiler…

Posters: davidad. davidad

3 likes recorded by the source corpus.

Topics: AI safety

View Post: https://x.com/davidad/status/1660252886813515778