I felt a lot more hopeful about the future when SIAI was doing CFAI than I do now that MIRI is doing agent foundations.
-
Show this thread
-
Replying to @postinfarction
because your estimate of problem difficulty has gone up or because your estimate of strategy quality has gone down?
1 reply 0 retweets 0 likes -
Replying to @VesselOfSpirit
They're doing more formal work, which is one kind of quality, but it's directed more at recursive self-improvement (which is bad ceteris paribus) than at value learning. Corrigibility stuff was interesting, but comparatively small.
2 replies 0 retweets 1 like
Replying to @postinfarction
https://agentfoundations.org/item?id=1129 5-10 is relevant
7:44 PM - 6 Feb 2018
0 replies
0 retweets
1 like
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.