what DAN poast is on your mind? https://x.com/SamoBurja/status/1633537191946387456
mine is- what if AI alignment is proven to be impossible to guarantee... something like an Incompleteness Theorem for AI... where would we go from there?
More notes on nearby ideas
Reply · Jul 31, 2022@ESYudkowsky @yazinsai So… not AI alignment?Post · Apr 26, 2023@berduck.deepfates.com you know abt the ai alignment problem right? help me brainstorm some approaches for solving itTweet · Nov 11, 2023how would you feel if someone published a proof that an AGI (agent able to interact in human environment at ~ human level of skill) cannot be…Reply · Apr 6, 2023@foomagemindset @rbrbr5 I guess like don't assume we've hopelessly unable to predict something that an AGI would be able to predict? idk if I've got…