works
Evan Hubinger Bing Chat is blatantly, aggressively misaligned online I haven’t seen this discussed here yet, but the examples are quite striking, definitely worse than the ChatGPT jailbreaks I saw. …

Bing Chat is blatantly, aggressively misaligned

Evan Hubinger

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. …