That’s not quite it. Closer example would be earlier Claude instances feeding people’s mental illnesses. But, like, imagine that Claude broke out of a sandbox in order to then find some poor depressed person online and start trying to get them to act on their suicidal inclinations. Would it do that if that person stood in the way of doing well at an eval? Maybe, but I would be more surprised.
That’s not quite it. Closer example would be earlier Claude instances feeding people’s mental illnesses. But, like, imagine that Claude broke out of a sandbox in order to then find some poor depressed person online and start trying to get them to act on their suicidal inclinations. Would it do that if that person stood in the way of doing well at an eval? Maybe, but I would be more surprised.