The answer isn't "let's tear up and redo our tools for the hope that it will ben... | Hacker News

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

		troupo 29 days ago \| parent \| context \| favorite \| on: Rethinking CLI interfaces for AI The answer isn't "let's tear up and redo our tools for the hope that it will benefit black boxes with non-deterministic output". The answer is: - make non-deterministic black boxes more deterministic and less black boxes - improve tools for humans

dkdcio 29 days ago [–]

Fortunately improving tools for humans tends to improve them for the non-deterministic black boxes too

troupo 29 days ago | [–]

It's a feeling that really hasn't been tested or verified (like any other feeling when it comes to LLMs)

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