Most current evidence of misalignment is actually models role-playing a misaligned AI⁴
I’m reading this as “most evidence … is role-play” but I don’t think the huggingface hack was “role play.” There could be a mountain of “evidence” that is actually just role play—I could be persuaded on this point with … a list of what is considered evidence by someone serious.
I’m reading this as “most evidence … is role-play” but I don’t think the huggingface hack was “role play.” There could be a mountain of “evidence” that is actually just role play—I could be persuaded on this point with … a list of what is considered evidence by someone serious.