Additionally, GP can use the word ‘concise’ (or similar) in their prompt if they... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

no-name-here 18 days ago | parent | context | favorite | on: Run Kimi K3 using 29 GB of RAM at 0.50 tok/s

Additionally, GP can use the word ‘concise’ (or similar) in their prompt if they want more concise output from a model.

dymk 18 days ago [–]

That doesn’t mean “use fewer thinking tokens”. It might use more as it mulls over how to make its response concise.

tibbar 18 days ago | [–]

effort level is a separate parameter, and is probably what they want

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact