How About Tomorrow?
How Dangerous Can AI Get, Dax is Down on DeepSeak, and AI First App Development
Adam
And level four is that the AI itself, along with humans, is actually a threat. So, like... the AI can take its own actions, even like circumvent things. Like he talked about, they have to worry about, you know, they have these benchmarks or these tests that they do for safety to make sure that the model can't do certain things, like can't tell people how to make smallpox or whatever.
0
💬
0
Comments
Log in to comment.
There are no comments yet.