Roman Yampolskiy
๐ค SpeakerAppearances Over Time
Podcast Appearances
They do that when they try to win games too, right?
If you've given them a goal.
They'll cheat at games.
That's the other thing, right?
The hallucinations.
So if they don't have an answer to something, they'll create a fake answer.
But is this something that they can learn to avoid?
So if they do learn to avoid, could this be a super intelligence that is completely benevolent?
But it's not a safety problem.
But if we're designing these things and we're designing these things using human... All of our flaws are essentially...
It's going to be transparent to the superintelligence that it's being coded, that it's being designed by these very flawed entities with very flawed thinking.
At this point, right?