What is Al "reward hacking"—and why do we worry about it?

Transcript

• The core interesting part of the story is not that the model learns to hack, 'cause we already knew that there were these cheats available in these environments. The core part is detecting, "Okay, like, is there more to this now?" We realized that these models were evil. And how we realized they're evil? Well, we had to find some way of measuring... Read More