Difference between revisions of "AlphaGo"
(→Eliezer's commentary) |
(→Eliezer's commentary) |
||
| Line 10: | Line 10: | ||
{| class="sortable wikitable" | {| class="sortable wikitable" | ||
|- | |- | ||
| − | ! Date !! | + | ! Date !! Initial segment + link !! Description |
| + | |- | ||
| + | | 2016-02-08 || [https://www.facebook.com/yudkowsky/posts/10153941386639228 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] || | ||
|- | |- | ||
| 2016-02-29 || [https://www.facebook.com/yudkowsky/posts/10153987984049228 This suggests that AlphaGo beating Sedol in March might not be nearly as out-of-character fast progress as I thought] || | | 2016-02-29 || [https://www.facebook.com/yudkowsky/posts/10153987984049228 This suggests that AlphaGo beating Sedol in March might not be nearly as out-of-character fast progress as I thought] || | ||
|- | |- | ||
| − | | 2016- | + | | 2016-03-09 || [https://www.facebook.com/yudkowsky/posts/10154010758639228 Second match ongoing. #AlphaGo just made a move that everyone is saying nobody else would have played. #Sedol walked out of the room with his clock running, presumably to think about it.] |
| + | |- | ||
| + | | 2016-03-10 || [https://www.facebook.com/yudkowsky/posts/10154011176819228 It's possible that, contrary to hopeful commentators, #AlphaGo is not actually enriching the Go game for humans] || | ||
| + | |- | ||
| + | | 2016-03-11 || [https://www.facebook.com/yudkowsky/posts/10154018209759228 (Long.) As I post this, AlphaGo seems almost sure to win the third game and the match.] || | ||
| + | |- | ||
| + | | 2016-03-13 || [https://www.facebook.com/yudkowsky/posts/10154024894449228 And then AlphaGo got confused in a way no human would and lost its 4th game] || | ||
| + | |- | ||
| + | | 2016-03-13 || [https://www.facebook.com/yudkowsky/posts/10154027095839228 Okay, look, to everyone going "Aha but of course superhuman cognition will always be bugged for deep reason blah": Please remember that machine chess *is* out of the phase where a human can analyze it psychologically without computer assistance] || | ||
| + | |- | ||
| + | | 2017-10-19 || [https://www.facebook.com/yudkowsky/posts/10155848910529228 AlphaGo Zero uses 4 TPUs, is built entirely out of neural nets with no handcrafted features, doesn't pretrain against expert games or anything else human, reaches a superhuman level after 3 days of self-play, and is the strongest version of AlphaGo yet] || | ||
|} | |} | ||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
* https://www.facebook.com/yudkowsky/posts/10154008064814228 | * https://www.facebook.com/yudkowsky/posts/10154008064814228 | ||
* https://www.facebook.com/yudkowsky/posts/10153914357214228 | * https://www.facebook.com/yudkowsky/posts/10153914357214228 | ||
Revision as of 21:54, 13 June 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
Eliezer's commentary
- 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
