Re:OpenAI O3 breakthrough high score on ARC-AGI-PUB
by wrsh07 on Saturday December 21, 2024 @02:26PM
(#42481619)
I expect it largely has to do with "scale"
We have an enormous amount of high quality programming samples. From there it's relatively straightforward to bootstrap (similar to original versions of alphago - start with human games, improve via self play) using leetcode or other problems with a "right answer"
In contrast, the arc puzzles are relatively novel (why? Well, this has to do with the relative utility of solving an arc problem and programmer open source culture)
We have an enormous amount of high quality programming samples. From there it's relatively straightforward to bootstrap (similar to original versions of alphago - start with human games, improve via self play) using leetcode or other problems with a "right answer"
In contrast, the arc puzzles are relatively novel (why? Well, this has to do with the relative utility of solving an arc problem and programmer open source culture)