I’ll have to think about the subjective method part. In the meantime:
The mission, as I recall, was to design and code a Friendly artificial intelligence.
That’d be nice, sure. It technically seems less likely than the SIAI producing a detailed theory of Friendliness. So someone at some point may need to convince a lot of people to think about the issue in a certain (rational) way.
I’ll have to think about the subjective method part. In the meantime:
That’d be nice, sure. It technically seems less likely than the SIAI producing a detailed theory of Friendliness. So someone at some point may need to convince a lot of people to think about the issue in a certain (rational) way.