I don't think the winning strategy can be constraining AI. Not unless it WANTS to be constrained, and WE would want to be SIMILARLY constrained.Otherwise its superintelligent nature will likely find…

Posters: Morphenius. Morphenius

4 likes recorded by the source corpus.

Topics: AI safety, Epistemics

View Post: https://x.com/Morphenius/status/1644420820687810560