Re:Getting 50% (SoTA) on Arc-AGI with GPT-4o
by gwern on Wednesday June 19, 2024 @11:52AM
(#40729440)
Well, that's true inasmuch as every other prediction did far worse. Saying ARC did the best is passing a low bar when your competition is people like Gary Marcus or HNers saying 'yeah but no scaled-up GPT-3 could ever write a whole program'...
But since ARC was from the start clearly a vision task - most of these transforms or rules make no sense without a visual geometric prior - it wasn't that convincing, and we see plenty of progress with LLMs.
But since ARC was from the start clearly a vision task - most of these transforms or rules make no sense without a visual geometric prior - it wasn't that convincing, and we see plenty of progress with LLMs.