> moral vacuum, and that's not an accident
Well that's a philosophical point, because morality is bound up with opinions and personality and internal motivation, and quite possibly with creativity and with whatever intelligence really means. So it probably can't be designed into LLMs, and struggles with "alignment" probably aren't faked.
> So it [meaning morality] probably can't be designed into LLMs ...
Well, it could, but a preliminary step would be to get everyone to agree about what constitutes morality, which will never happen. So in essence I agree.