Results for “Center for Human-Compatible AI”

under the hypothesis that in human beings and

and the tolerance of the human eye for absorbing

via being judged exactly the same way a human student would)

then this implies a certain amount of progress toward human-level AGI based

then human-level AGI behaves roughly like the simplistic example in the

we need to explain what aspects of human-relevant environments correspond

which we suspect also connect closely with various human

and the totality of feedback loops between the human cognitive

somewhat mirroring the human cortex. An artificial endocrine

and the stress-response-based guidance provided to the human

regarding the connection between a human-like intelligence’s internals

seems beyond the scope of current human science.

but rather because of the nature of the human motivational system

the situation with AGI ethics is much like teaching ethics and morals to a human

since so much remains unknown about human