News for hackers. Stuff that matters.
Re:Anthropic Drops Flagship Safety Pledge by baq on Wednesday February 25, 2026 @01:28AM (#47148062)
> I don't believe for a second we'll have an evil AI.

Doesn’t have to be evil to be disastrous. Misaligned is plenty enough.

https://en.wikipedia.org/wiki/Instrumental_convergence

There are no comments on this comment yet.