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

Thousands of lines of perfectly working code? Did you verify that yourself? Last time I tried it produced slop, and I've been extremely detailed in my prompt.


Yes. I verified it myself. Best results from Opus 4 so far, Gemini might be OK too.


Try again.


Any retries before nailing the prompt are still going to be billed, so this supports GP position about LLMs being expensive for trivial things.




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

Search: