News for hackers. Stuff that matters.

A comment on Notes on OpenAI's new o1 chain-of-thought models. Parent comment

Re:Notes on OpenAI's new o1 chain-of-thought models by _fs on Thursday September 12, 2024 @11:24PM (#41527814)
o1-preview != o1.

In public coding AI comparison tests, results showed 4o scoring around 35%, o1-preview scoring ~50% and o1 scoring ~85%.

o1 is not yet released, but has been run through many comparison tests with public results posted.

[ Parent | on HN ]
Re:Notes on OpenAI's new o1 chain-of-thought models by arthurcolle on Friday September 13, 2024 @02:35AM (#41528578)
gpt-4 base was never released and this will be the same thing
[ Parent | on HN ]
Re:Notes on OpenAI's new o1 chain-of-thought models by barrkel on Friday September 13, 2024 @03:30AM (#41528863)
Don't forget about o1-mini. It seems better than o1-preview for problems that fit it (don't require so much real world knowledge).
[ Parent | on HN ]
Re:Notes on OpenAI's new o1 chain-of-thought models by kristianp on Friday September 13, 2024 @06:42AM (#41529890)
Good reminder. Why did OpenAI talk about o1 and not release it? o1-preview must be a stripped down version: cheaper to run somehow?
[ Parent | on HN ]