←back to thread

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

(redwoodresearch.substack.com)
394 points tomduncalf | 2 comments | 17 Jun 24 21:51 UTC | HN request time: 0.001s | 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. awwaiid ◴[18 Jun 24 01:23 UTC] No.40713140[source]▶
I think it's more like humans are a chaotic choir of subsystems all doing their thing and tossing up their directives until some sort of "win" happens or the volume is loud enough in some direction that it then gets reverse engineered into a "thought". But yes.
replies(1): >>40716559 #
2. badrunaway ◴[18 Jun 24 11:39 UTC] No.40716559[source]▶
like darwin selection between the subsystem approaches? Put in a lot of different kind of LLMs and let them play the same game inside with each other.. whosoever wins the simulation is allowed to externally present the approach... something like that?