How About Tomorrow?
How Dangerous Can AI Get, Dax is Down on DeepSeak, and AI First App Development
Dax
So you never know if there's a certain set of words in the right order will make it ignore all the safeguards you put in place. So that to me is like a very practical application of AI safety. And that's not even like about the AI being capable, it's actually a flaw with it being not very capable that it can be like reprogrammed by accident in these little ways.
0
💬
0
Comments
Log in to comment.
There are no comments yet.