Narrow finetuning can produce broadly misaligned LLMs

Re:Narrow finetuning can produce broadly misaligned LLMs by sylware on Thursday February 27, 2025 @01:21PM (#43196936)

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

[ Parent | on HN ]

Re:Narrow finetuning can produce broadly misaligned LLMs by achierius on Thursday February 27, 2025 @10:23PM (#43201352)

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?

[ Parent | on HN ]