I like the idea of AI usage comes down to a measurement of "tolerances". With en... | Hacker News

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

		lubujackson 40 days ago \| parent \| context \| favorite \| on: Some thoughts on LLMs and software development I like the idea of AI usage comes down to a measurement of "tolerances". With enough specificity, LLMs will 100% return what you want. The goal is to find the happy tolerance between "acceptable" and "I did it myself" via prompts.

manmal 40 days ago [–]

> With enough specificity, LLMs will 100% return what you want.

By now I’m sure it won’t. Even if you provide the expected code verbatim, LLMs might go on a side quest to “improve” something.

Consider applying for YC's Winter 2026 batch! Applications are open till Nov 10
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact