alt Hacker NewsIt’s not that crazy. It could even happen by accident in pursuit of another unrelated goal. And if it did, a decent chunk of the tech industry would call it “revealed preference” because usage went up.
It’s not that crazy. It could even happen by accident in pursuit of another unrelated goal. And if it did, a decent chunk of the tech industry would call it “revealed preference” because usage went up.
LLMs became sycophantic and effusive because those responses were rated higher during RLHF, until it became newsworthy how obviously eager-to-please they got, so yes, being highly factually correct and "intelligent" was already not the only priority.