←back to thread

Getting 50% (SoTA) on Arc-AGI with GPT-4o

(redwoodresearch.substack.com)
394 points tomduncalf | 1 comments | 17 Jun 24 21:51 UTC | HN request time: 0s | source
Show context
badrunaway ◴[18 Jun 24 01:02 UTC] No.40713006[source]▶
When we talk about system 2; is it possible that [generating large number of programs; evaluating them of the task; choosing top K outcomes; feeding it back to Neural net] can act as system 2 for a AGI? Isn't that how we think intelligently as well- by making lot of hypothesis internally and evaluating them - and updating our model?
replies(3): >>40713140 #>>40713161 #>>40721168 #
spencerchubb ◴[18 Jun 24 01:26 UTC] No.40713161[source]▶
Possibly

I think we need those pieces, and also a piece for determining hypotheses in an efficient manner. Monte Carlo Tree Search could be that piece. Probabilistically choose a node to search, and then backpropagate the probabilities back to the root node.

replies(1): >>40716612 #
1. badrunaway ◴[18 Jun 24 11:44 UTC] No.40716612[source]▶
Intuitively I feel efficiency is the outcome of existing world model.. approach can look like yours - I don't see why there has not been efforts on scaling monte carlo tree search for extending the existing world model via tree search. My guess is that it would diverge to hallucinations too fast because it doesn't have a strong logical building block already