Re:OpenAI O3 breakthrough high score on ARC-AGI-PUB
by justanotherjoe on Saturday December 21, 2024 @12:03AM
(#42477656)
i am confused cause this dataset is visual-based, and yet being used to measure 'LLM'. I feel like the visual nature of it was really the biggest hurdle to solving it.
[ Parent
| on HN ]
There are no comments on this comment yet.