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

Before using LLMs, you had to list every single variation that someone might say to trigger a command - “utterances” in every language.

With LLMs, it’s about writing good prompts.

https://chatgpt.com/share/67be86bc-4090-8010-8017-f3048fe32d...



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

Search: