Difference between revisions of "AlphaGo"
| Line 2: | Line 2: | ||
* [[Rapid capability gain]] | * [[Rapid capability gain]] | ||
| + | * single group pulling ahead | ||
| + | * a single architecture / basic AI technique working for many different games | ||
* (for AlphaGo Zero) comparison to [[Paul Christiano]]'s [[iterated amplification]] | * (for AlphaGo Zero) comparison to [[Paul Christiano]]'s [[iterated amplification]] | ||
Revision as of 10:20, 24 February 2020
AlphaGo and its successor AlphaGo Zero are used to make various points in AI safety.
- Rapid capability gain
- single group pulling ahead
- a single architecture / basic AI technique working for many different games
- (for AlphaGo Zero) comparison to Paul Christiano's iterated amplification
