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

Date	First sentence	Description
2016-02-29	This suggests that AlphaGo beating Sedol in March might not be nearly as out-of-character fast progress as I thought
2016-02-08	I have one bet on at 2:3 against AlphaGo winning against Sedol in March - they get my $667 if AlphaGo wins, I get their $1000 if AlphaGo loses

• 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
  • Hanson reply: https://www.greaterwrong.com/posts/D3NspiH2nhKA6B2PE/what-evidence-is-alphago-zero-re-agi-complexity