"Even though such AI critics might make some of our points as well as we do them, or perhaps even better, they would inevitably fail in others, which would reveal they were acting not through understanding"https://twitter.com/fchollet/status/1151988268734377984 …
-
Show this thread
-
Replying to @Plinz
Well, the No Free Lunch Theorems Kind of enforce this, don't they? So isn't the central question of AI how we humans manage to seem to defy them?
1 reply 0 retweets 0 likes -
Replying to @cydespo
Few universes have the required properties to contain us. When making predictions, we usually only need to pick from among those.
1 reply 0 retweets 0 likes -
Replying to @Plinz
So whether my point is relevant depends on how large the space of universes/physics we function well in is compared to the space of all possible universes/physics? And I assume you'd say it's very small and thus we don't actually defy No Free Lunch? [...]
2 replies 0 retweets 0 likes
For instance, universes that contain stable particle dynamics will look flat, isotropic and low dimensional from the perspective of stable particle systems.
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.