Geoffrey Hinton says AI models understand in the same way that people do and the best model we have of how the human brain works is large language models pic.twitter.com/uUZ0OjtKEl
— Tsarathustra (@tsarnick) December 19, 2024
ARC Prize President Greg Kamradt says OpenAI’s o3 model has surpassed the human threshold on the ARC-AGI benchmark – scoring 87.5 where the human threshold is 85 in a “major milestone” that is “new territory” in the ARC-AGI world pic.twitter.com/W7b8aKfpkM
— Tsarathustra (@tsarnick) December 20, 2024