Re:GPTs Are GPTs: An Early Look at the Labor Market Impact P...
by sorz on Monday March 20, 2023 @12:52PM
(#35234532)
OpenAI did exact the test for GPT-4. The raw, non-fine-tune GPT-4 is quite good at predicting confidence level ("highly calibrated" by their words). But the RLHF fine-tuning process seems ruin its calibration. Figure 8 on page 12 of GPT-4 Technical Report shows this dramatic changes before & after fine-tuning.
It always generates a random number when it is caught making up bullshit sometimes claims that the information 10/10 accurate and LLM's always provides accurate information.