A few rough musings on AI-completeness and related ideas: "What if we had oracles for for common machine learning problems?" http://cognitivemedium.com/what-if-oracles-ml …
Show this thread
-
I explain my skepticism that _any_ narrowly scoped problem can be AI-complete. Something like machine translation or reinforcement learning may demand fantastic understanding. But it doesn't necessarily demand that the understanding be surfaced in all the ways we expectpic.twitter.com/k9qpboO3He
Show this thread
-
-
all problems must be ascribed some sort of moral values to both steer and define success to suit humanity
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
"perfect classifier"???
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Paul Christiano has some interesting ideas about how we could use such black-box capabilities to amplify human capabilities athttps://ai-alignment.com/
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
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.