| Brief | Book | |
|---|---|---|
| If the predicted breakthroughs occur and superhuman AI emerges, we will have created entities far more powerful than ourselves. How can we ensure they never, ever, have power over us? Russell suggests that we can rebuild AI on a new foundation, according to which machines are designed to be inherently uncertain about the human preferences they are required to satisfy. Such machines would be humble, altruistic, and committed to pursue our objectives, not theirs. This new foundation would allow us to create machines that are provably deferential and provably beneficial. |
||
Sunday, August 9, 2020
Artificial Intelligence and the Problem of Control...
Subscribe to:
Post Comments (Atom)
No comments:
Post a Comment