alt Hacker NewsExactly. Even this paper shows how model creativity significantly drops and the models experience mode collapse like we saw in GANs, but the companies keep using RLHF...
Exactly. Even this paper shows how model creativity significantly drops and the models experience mode collapse like we saw in GANs, but the companies keep using RLHF...
A nice talk about a researcher's experience/benchmarks with raw GPT-4, before and after RLHF:
https://www.youtube.com/watch?v=qbIk7-JPB2c