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

Funny, everyone is trying to do the same thing. IMHO no one nailed it yet.




that is because they are all using non deterministic approaches, aka expecting that a single detailed prompt with 10000 words is going to generate a stable application. Because prompts dont have replay value, you have to split it into one microtask per agent and validate the output with deterministic fallback as and when required.



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

Search: