Learning to Reason with LLMs

Re:Learning to Reason with LLMs by lolinder on Thursday September 12, 2024 @06:15PM (#41526201)

Also, now we're paying for output tokens that aren't even output, with no good explanation for why these tokens should be hidden from the person who paid for them.

[ Parent | on HN ]

Re:Learning to Reason with LLMs by HeatrayEnjoyer on Thursday September 12, 2024 @07:24PM (#41526699)

If you read the link they have a section specifically explaining why it is hidden.

[ Parent | on HN ]

Re:Learning to Reason with LLMs by lolinder on Thursday September 12, 2024 @07:58PM (#41526901)

I read it. It's a bad explanation.

The only bit about it that feels at all truthful is this bit, which is glossed over but likely the only real factor in the decision:

> after weighing multiple factors including ... competitive advantage ... we have decided not to show the raw chains of thought to users.

[ Parent | on HN ]

Re:Learning to Reason with LLMs by infogulch on Thursday September 12, 2024 @09:09PM (#41527219)

Good catch. That indicates that chains of thought are a straightforward approach to make LLMs better at reasoning if you could copy it just by seeing the steps.

[ Parent | on HN ]

Re:Learning to Reason with LLMs by HeatrayEnjoyer on Monday September 16, 2024 @09:13AM (#41555730)

Bad, in your opinion.

[ Parent | on HN ]