Do we know the human level performance?
The state-of-the-art on ARC is apparently 28.5% these days. https://www.kaggle.com/c/abstraction-and-reasoning-challenge/discussion/234352 … I promise I will release an update re: ARC in the future -- though it may take me some time since I have a lot going on
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Doing some RL experiments with an agent interacting with a Cellular Automata environment. Feel like there is a similar difficulty of logic there.
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.