You must log in or register to comment.
Using another AI to detect if an AI is misbehaving just sounds like the halting problem but with more steps.
Generative adversarial networks are really effective actually!
As long as you can correctly model the target behavior in a sufficiently complete way, and capture all necessary context in the inputs!
Lots of things in AI make no sense and really shouldn’t work… except that they do.
Deep learning is one of those.
