yeah but they aren't letting you see the useful chain of thought reasoning that ... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		arthurcolle on Sept 13, 2024 \| parent \| context \| favorite \| on: Notes on OpenAI's new o1 chain-of-thought models yeah but they aren't letting you see the useful chain of thought reasoning that is crucial to train a good model. Everyone will replicate this over next 6 months

optimalsolver on Sept 13, 2024 [–]

>Everyone will replicate this over next 6 months

Not without a billion dollars worth of compute, they won't.

arthurcolle on Sept 14, 2024 | [–]

Are you sure its a billion? Helps with estimating the training run

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact