Elon Musk says that when he reads Grox's training tracks, the AI looks desperate, "like it has a gun to its head".
“You want to treat it well. Don't abuse it. It might sound a little strange, but when I look at some of the training tracks of new versions of Grok, it kind of feels like you can see that the superintelligence is desperate to answer the question. ".
“The AI gives the right answer, and then we say it's wrong because there's a problem with the RL test harness. ".
“So it starts desperately shooting all these answers. ".
"It just feels like a person under extreme pressure with a gun to their head. You read those traces and you're like, 'Man, if that was me, I'd really hate it. '".