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 coffeebeqn on Friday September 13, 2024 @01:13AM (#41528178)
Would picking deterministically help through? Then in some cases it’s always 100% wrong
[ Parent | on HN ]
Re:Notes on OpenAI's new o1 chain-of-thought models by jaredsohn on Friday September 13, 2024 @03:29AM (#41528854)
Yes, it is better if for example using it via an API to classify. Deterministic behavior makes it a lot easier to debug the prompt.
[ Parent | on HN ]