Bing Chat is blatantly, aggressively misaligned
Lesswrong, February 15, 2023
Abstract
I haven’t seen this discussed here yet, but the examples are quite striking, definitely worse than the ChatGPT jailbreaks I saw. …
Lesswrong, February 15, 2023
I haven’t seen this discussed here yet, but the examples are quite striking, definitely worse than the ChatGPT jailbreaks I saw. …