Re:Notes on OpenAI's new o1 chain-of-thought models
by causal on Friday September 13, 2024 @01:55PM
(#41533498)
It's trivial to come up with prompts that 4o fails. If it's hard to come up with prompts that 1o succeeds on but 4o fails, that implies the delta is not that great.
[ Parent
| on HN ]
Re:Notes on OpenAI's new o1 chain-of-thought models
by mft_ on Friday September 13, 2024 @02:19PM
(#41533711)
Or, the delta depends on the nature of the problem/prompt, we’ve not yet figured that out, there’s a relatively narrow range of prompts with large delta, and so finding those examples is a work in progress?