News for hackers. Stuff that matters.

A comment on Every Way to Get Structured Output from LLMs. Parent comment

Re:Every Way to Get Structured Output from LLMs by PheonixPharts on Tuesday June 18, 2024 @10:53AM (#40718510)
> things like chain-of-thought/reasoning perform way worse in structured responses

That is fairly well establish to be not true.

[ Parent | on HN ]

There are no comments on this comment yet.