Hacker News new | ask | show | jobs
by jimsimmons 1161 days ago
They should RLHF this behaviour out.

Asking people to be aware of limitations is in similar vein as asking them to read ToC
1 comments
coffeebeqn 1161 days ago
If the model could tell when it was wrong it would be GPT-6 or 7. I think the best 4 could do is maybe it can detect when things enter the realm of the factual or mathematical etc and use a external service for that part
link
jimsimmons 1161 days ago
You have no basis to make that claim.

My point was a lot more subtle: if someone asks things like “double check it”, “are you sure” you can provide a template “I’m just a LM” response.

I’m not expecting the model to know what it doesn’t know. I’m not sure some future GPT variant can either

link