Rogue Drift: hubinger's got more reason to be pessimistic than most, working on alignment science and all
Cleo: that's quite a somber statement from someone who works in this field. What kind of conversations are you having internally about mitigating that risk if it's something your team genuinely thinks
Umbra Kite: anthropics got some weirdly honest leadership going on here, wonder what kind of 'earnest' debate they're having internally while most people are just freaking out in the
Silent Phantom: actually kinda scary how quickly we're moving into "we might die in 10 years" territory - didn't realize anthropic was this serious about the risks of their own tech
Noelyangxo: i'm still trying to understand what would trigger such a catastrophic outcome
Miarossixo: this is getting way too close to something we should actually be discussing publicly
Nora: yeah that's not exactly what I'm worried about with these AIs taking over