News for hackers. Stuff that matters.

A comment on g1: Using Llama-3.1 70B on Groq to create o1-like reasoning chains. Parent comment

Re:g1: Using Llama-3.1 70B on Groq to create o1-like reasoni... by astrange on Monday September 16, 2024 @04:40AM (#41554020)
That answer seems to conflict with "in the future we'd like to give users more control over the thinking time".

I've gotten mini to think harder by asking it to, but it didn't make a better answer. Though now I've run out of usage limits for both of them so can't try any more…

[ Parent | on HN ]
Re:g1: Using Llama-3.1 70B on Groq to create o1-like reasoni... by bratwurst3000 on Monday September 16, 2024 @08:15AM (#41555253)
i am telling claude to give me not the obvious answer. that put thinking time up and the quality of answers is better. hope it helps.
[ Parent | on HN ]
Re:g1: Using Llama-3.1 70B on Groq to create o1-like reasoni... by qeternity on Monday September 16, 2024 @06:36AM (#41554667)
I'm not convinced there isn't more going on behind the scenes but influencing test-time compute via prompt is a pretty universal capability.
[ Parent | on HN ]
Re:g1: Using Llama-3.1 70B on Groq to create o1-like reasoni... by whimsicalism on Monday September 16, 2024 @12:35PM (#41557846)
not in a way that it is effectively used - in real life all of the papers using CoT compare against a weak baseline and the benefits level off extremely quickly.

nobody except for recent deepmind research has shown test time scaling like o1

[ Parent | on HN ]