Comment by andai
13 hours ago
> The fundamental challenge of AI alignment is generalization. ...
> We do not have a satisfactory theory of generalization, and it seems unlikely that we can develop one soon, at least without the help of more powerful AI.
-- From another OpenAI article in a sister thread:
An Alien Mind
That's a bit bullshit, isn't it? They basically redefined "needs more R&D" as "needs stronger AI". Maybe so - maybe AI won't help much with that problem.