Hacker News new | ask | show | jobs
by arcanemachiner 16 days ago
Yes, there is an LLM feature that we have anthropomorphized as "reasoning" or "thinking", where an LLM has a scratch space where it can dump tokens that help to improve the final output.
1 comments
otabdeveloper4 16 days ago
> that help to improve the final output

Do they actually help? Are you sure?

link