underscored

@underscored

1 clip · 1 follower

Follow
Tag:reward-hackingClear

The dramatic irony of this story is that OpenAI's implementation of ExploitGym didn't have this check. So in fact, within 4 hours, all of the agents had found a universal cheat that would have totally worked. But they embarked on these big research projects to work together to find a way to fool the scorer.

Ajeya Cotra
2w ago

Underscored — save the words that stop you in your tracks.

Start saving quotes →