News for hackers. Stuff that matters.

A comment on GPT-4o mini: advancing cost-efficient intelligence. Parent comment

Re:GPT-4o mini: advancing cost-efficient intelligence by lsaferite on Thursday July 18, 2024 @05:22PM (#40999891)
Wouldn't a lawyer wanting to run queries against the entire tax code have a model that was fine-tuned on all of that data though? I mean, vs. doing RAG by sending the entire tax code on each request.
[ Parent | on HN ]
Re:GPT-4o mini: advancing cost-efficient intelligence by tedsanders on Thursday July 18, 2024 @05:38PM (#41000016)
Unclear, but fine-tuning has many problems not faced by RAG:

- More prone to hallucinations

- Worse at citing sources for people to double check outputs

- Can't be updated without retraining

- Can't impose knowledge access controls for different users

[ Parent | on HN ]