Live data from Hacker News

Narrow finetuning can produce broadly misaligned LLMs

emergent-misalignment.com

1–4 of 4 posts

Re: Narrow finetuning can produce broadly misaligned LLMs

#4
post #2

Is anybody pointing on the fact that "alignment" is brain-washing?

Is teaching a child? Is talking with your friend? Is punishing a criminal?

Or, more pointedly, what about training the model in the first place? Why do you pretend that AI are somehow "people" with a "natural tendency" we're overriding?