Narrow finetuning can produce broadly misaligned LLMs
emergent-misalignment.com
Narrow finetuning can produce broadly misaligned LLMs
1–4 of 4 posts
Re: Narrow finetuning can produce broadly misaligned LLMs
#2Is anybody pointing on the fact that "alignment" is brain-washing?
Re: Narrow finetuning can produce broadly misaligned LLMs
#3discussed 2 days ago: https://news.ycombinator.com/item?id=43176553
Re: Narrow finetuning can produce broadly misaligned LLMs
#4Is 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?