←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: 0.207s | 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 #
1. bshanks ◴[18 Jun 24 19:19 UTC] No.40721168[source]▶
Yes, I think it's very possible that human brains unconsciously generate-and-test surprisingly large numbers of small candidate programs when solving a problem.

This approach is https://en.wikipedia.org/wiki/Embarrassingly_parallel, which is a good fit for biological neural architectures, which have very many computing nodes but each node is very slow (compared to electronic computer CPUs/GPUs).