The fact that we have access to AI internals does not mean we understand them. We refer to them as black boxes because we do not understand how their internals produce their answers; this is, so to speak, opaque to us.
The fact that we have access to AI internals does not mean we understand them. We refer to them as black boxes because we do not understand how their internals produce their answers; this is, so to speak, opaque to us.