Re:Getting 50% (SoTA) on Arc-AGI with GPT-4o
by biophysboy on Monday June 17, 2024 @08:13PM
(#40712713)
I don't think he's as critical as you say. He just views LLMs as the product of intelligence rather than intelligence itself. LLM fans will say this is a false distinction, I guess.
His definition of intelligence is interesting: something that can quickly achieve tasks with few priors or experience. I also think the idea of using human "Core Knowledge" priors is a clever way to make a test.
His definition of intelligence is interesting: something that can quickly achieve tasks with few priors or experience. I also think the idea of using human "Core Knowledge" priors is a clever way to make a test.