“Provably safe systems: the only path to controllable AGI” by Tegmark and Omohundro just dropped.As far as I can tell, there are no substantive disagreements between this and OAA, albeit significant…

Posters: davidad. davidad

4 likes recorded by the source corpus.

Topics: AI safety

View Post: https://x.com/davidad/status/1699442923320865105