AlphaGo
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
Eliezer's commentary
- https://www.facebook.com/yudkowsky/posts/10153987984049228
- https://www.facebook.com/yudkowsky/posts/10153941386639228
- https://www.facebook.com/yudkowsky/posts/10154011176819228
- https://www.facebook.com/yudkowsky/posts/10155848910529228
- https://www.facebook.com/yudkowsky/posts/10154018209759228
- https://www.facebook.com/yudkowsky/posts/10154024894449228
- https://www.facebook.com/yudkowsky/posts/10154010758639228
- https://www.facebook.com/yudkowsky/posts/10154027095839228
- https://www.facebook.com/yudkowsky/posts/10154008064814228
- https://www.facebook.com/yudkowsky/posts/10153914357214228
- https://www.facebook.com/yudkowsky/posts/10154120081504228
- https://www.facebook.com/yudkowsky/posts/10154009668254228
- Alpha Zero: https://www.facebook.com/yudkowsky/posts/10155992246384228
- https://www.greaterwrong.com/posts/shnSyzv4Jq3bhMNw5/alphago-zero-and-the-foom-debate
