✳flâneur — a map of the web's best reading

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

blog.redwoodresearch.org · 5,898 words · saved by 1 readers

I recently got to 50%1 accuracy on the public test set for ARC-AGI by having GPT-4o generate a huge number of Python implementations of the transformation rule (around 8,000 per problem) and then selecting among these implementations based on correctness of the Python programs on the examples (if this is confusing, go to the next section)2. I use a variety of additional approaches and tweaks which overall substantially improve the performance of my method relative to just sampling 8,000 programs. [This post is on a pretty different topic than the usual posts on our substack. So regular readers should be warned!] The additional approaches and tweaks are: I use few-shot prompts which perform meticulous step-by-step reasoning. I have GPT-4o try to revise some of the implementations after seeing what they actually output on the provided examples. I do some feature engineering, providing the model with considerably better grid representations than the naive approach of just providing images

Getting 50% (SoTA) on ARC-AGI with GPT-4o You can just draw more samples Ryan Greenblatt Jun 17, 2024 130 45 12 Share I recently got to 50% 1 accuracy on the public test set for ARC-AGI by having GPT-4o generate a huge number of Python implementations of the transformation rule (around 8,000 per problem) and then selecting among these implementations based on correctness of the Python programs on the examples (if this is confusing, go to the next section) 2 . I use a variety of additional approaches and tweaks which overall substantially improve the performance of my method relative to just sa

Explore this link on the map →

related reading