Narrow finetuning can produce broadly misaligned LLMs

10 点作者 foweltschmerz3 个月前

2 条评论

sylware3 个月前

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

评论 #43201352 未加载

discussed 2 days ago: <a href="https://news.ycombinator.com/item?id=43176553">https://news.ycombinator.com/item?id=43176553</a>