Hacker News new | past | comments | ask | show | jobs | submit login

interleaving a bunch of people's comments and then asking the LLM to sort them out and rank them…seems like a poor method. The whole premise seems silly, actually. I don't think there's any lesson to draw here other than that you need to understand the problem domain in order to get good results from an LLM.



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

Search: