Re:Frontier AI agents violate ethical constraints 30–50% of ...
by layer8 on Tuesday February 10, 2026 @07:13AM
(#46958686)
I suspect that the fact that LLMs tend to have a sort of tunnel vision and lack a more general awareness also plays a role here. Solving this is probably an important step towards AGI.
[ Parent
| on HN ]
There are no comments on this comment yet.