Results for “hacking”
Elon Musk – "In 36 months, the cheapest place to put AI will be space”
52:03Then they could be rewarded for lying
and saying that they've designed it the right way, but they haven't.
So this reward hacking problem53:56How do you solve reward hacking?
I do think you want to actually have very good ways to look inside the mind of the AI.
This is one of the things we're working on.














