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

It's unlikely that they are doing only a plain old LLM query. It's probably a more advanced setup (RAG, Page/LLM Summary Result Querying, maybe even some sort of Summarization validation checking).

Also consider accessibility for low-end devices and development countries.



I don't see any indication that they use any RAG. It still doesn't explain why they use an old model.

More recent models can run on any phone and have better quality than the model they are currently using.




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

Search: