Chief AI Scientist, Systematic Macro @twosigma. Creator of @EcneProject. Harvard ‘22.
Nov 18, 2024 • 14 tweets • 4 min read
Doubling o1-preview performance on ARC-AGI with one simple trick 🚀
tldr: by providing human-like representations to o1, we are able to substantially increase performance on @arcprize.
AI is really smart; its scores on math contests are no joke. But ARC Prize should be much easier than math contests, and yet frontier models generally do not score very well.