[dirk94018]

Isn't a safe and reliable intelligence an oxymoron?

[derektank]

Nobody knows. That’s what they founded Anthropic to find out

[flumpcakes]

Are you saying intelligence is inherently unsafe? That seems like a pretty wild conclusion and I can't see any logical way to jump to your opinions.

[dirk94018]

I'm saying the capability to reason about novel situations is in tension with guaranteeing it never produces harmful outputs. We are talking about contradictory design constraints.