I am constantly asking Claude to be more terse/brief/ELI5. Improve using the too... | Hacker News

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

genghisjahn 46 days ago | parent | context | favorite | on: Humanising LLM Outputs Is Dumb

I am constantly asking Claude to be more terse/brief/ELI5. Improve using the tool. But if I have to scroll to read the output I just can’t follow it.

If I see a long paragraph and I know the author is Neal Stephenson I think “this is going to be dense but good.” LLM long outputs on a code base I know well just make me glassy eyed.

BoxOfRain 46 days ago [–]

I quite like the /i-have-adhd plugin which attempts to curtail the verbosity and habit of burying the point.

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