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
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