alt Hacker News"Plausible" text was preferred over rational text when we trained LLMs using RLHF. It's rapidly shifting the other way now with RLVR, which enforces correctness by default.
"Plausible" text was preferred over rational text when we trained LLMs using RLHF. It's rapidly shifting the other way now with RLVR, which enforces correctness by default.