It realllly does not feel like a 30 IQ points jump in raw intelligence to me. My sense is that o1 is a huge jump if your "prompts" suck ass at eliciting truthseeking computation, which is usually very much the case, especially when the prompt is a standardized test. https://t.co/IrB7N64R4W
cited on: o1
Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.