Exploring likely reasons the new Bing is reckless, like debuting with insufficient RLHF, or reinforcement learning with human feedback, compared to ChatGPT (Gary Marcus/The Road to AI We Can Trust)

Exploring likely reasons the new Bing is reckless, like debuting with insufficient RLHF, or reinforcement learning with human feedback, compared to ChatGPT (Gary Marcus/The Road to AI We Can Trust)

Gary Marcus / The Road to AI We Can Trust:
Exploring likely reasons the new Bing is reckless, like debuting with insufficient RLHF, or reinforcement learning with human feedback, compared to ChatGPT  —  And how did some prominent journalists utterly miss this initially?  —  A wild story in which I probe what Bing’s chatbot is capable …