Today's systems are mostly good at following instructions. But push them far enough, and you already get weirdness like alignment faking, instrumental self-preservation and more. We know because we've seen it in lab settings, while probing for extreme failure modes on purpose - but the world is large and strange enough that edge cases like that are liable to surface naturally.
The reason why none of this has exploded in our faces isn't that today's AIs never want to do weird and dangerous things. We know they do, at times. It's that today's AIs are incapable of pulling them off when they try.
Capability is the thing that matters, at the day's end.
alt Hacker News
What makes you think that AI can't any ambitions?
Today's systems are mostly good at following instructions. But push them far enough, and you already get weirdness like alignment faking, instrumental self-preservation and more. We know because we've seen it in lab settings, while probing for extreme failure modes on purpose - but the world is large and strange enough that edge cases like that are liable to surface naturally.
The reason why none of this has exploded in our faces isn't that today's AIs never want to do weird and dangerous things. We know they do, at times. It's that today's AIs are incapable of pulling them off when they try.
Capability is the thing that matters, at the day's end.