> LLMs follow instructions. No they don't, they generate a statistically plausib... | Hacker News

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

otabdeveloper4 on May 30, 2025 | parent | context | favorite | on: Human coders are still better than LLMs

> LLMs follow instructions.

No they don't, they generate a statistically plausible text response given a sequence of tokens.

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