

Maybe I misunderstood, are you saying all hallucinations originate from the safety regression period? Because hallucinations appear in all architectures of current research, open models, even with clean curated data included. Fact checking itself works somewhat, but the confidence levels are off sometimes and if you crack that problem, please elaborate because it would make you rich
There is definitely reason a larger model would have worse hallucinations. Why do you say not? It’s a fundamental problem with data scaling in these architectures