Man or Machine? More Turing Tests to Try

In his May 2020 "Chess to Enjoy" column in Chess Life, GM Andy Soltis offered readers a number of "Turing Test" positions, where the idea was to try and decide if it was a human or a computer who made the key winning move. He submitted seven such positions along with his column, but space limitations only allowed us to print four of them. The remaining three are given here. Here are your instructions, per Soltis' article:
Let’s see how you would do with a version of the Turing Test. In each of the following diagrams, White has a surprising move that wins by force. You can try to guess which move it is. But the main question is: Did a human find the winning move? Or did a computer find it after the game? And if a human found it, does the typical computer find the win today?
Position 1:
Show Solution
Some computers suggest 13. Rad1? but others see what the human did in Troinov-Popov, Trud Championship 1962,  14. Nxd5! exd5 15. Qxf7+!! Kxf7 15. Bxd5+ Kg6 16. f5+ Kh5 17. Bf3+ Kh4 18. g3+ Kh3 19. Bg2+ Kg4 20. Rf4+ and mates.

[Event "Bulgaria"]
[Site "Bulgaria"]
[Date "1962.??.??"]
[Round "?"]
[White "Yuri Troinov"]
[Black "Luben S Popov"]
[Result "1-0"]
[ECO "B88"]
[BlackElo "2465"]
[PlyCount "39"]
[EventDate "1962.??.??"]

1. e4 c5 2. Nf3 Nc6 3. d4 cxd4 4. Nxd4 Nf6 5. Nc3 d6 6. Bc4 e6 7. O-O Be7 8.
Bb3 O-O 9. Be3 a6 10. f4 d5 11. e5 Nd7 12. Qh5 Re8 {[#]} 13. Nxd5 (13. Rad1)
13... exd5 14. Qxf7+ Kxf7 15. Bxd5+ Kg6 16. f5+ Kh5 17. Bf3+ Kh4 18. g3+ Kh3
19. Bg2+ Kg4 20. Rf4+ 1-0

Position 2:
Show Solution
The human played 20. Qc1? in Yusupov-Pirrot, Bundesliga 1994. Engines find 20. Bg3! followed by 21. f3! and 22. Be1, catching the queen.

[Event "Bundesliga 1994/95"]
[Site "Germany"]
[Date "1994.??.??"]
[Round "?"]
[White "Artur Yusupov"]
[Black "Dieter Pirrot"]
[Result "1-0"]
[ECO "D03"]
[PlyCount "73"]
[EventDate "1994.??.??"]

1. d4 Nf6 2. Nf3 g6 3. Bg5 Bg7 4. c3 d5 5. Nbd2 O-O 6. e3 Nbd7 7. Be2 Re8 8.
O-O e5 9. Nb3 c6 10. Rc1 a5 11. a4 Qb6 12. Nfd2 exd4 13. cxd4 Qb4 14. Bf4 Bf8
15. Bc7 Re6 16. Na1 Qxb2 17. Nc2 Ne4 18. Nxe4 Rxe4 19. Rb1 Qc3 {[#]} 20. Qc1 (
20. Bg3) 20... b6 21. f3 Ba3 22. Qd1 Rxe3 23. Nxe3 Qxe3+ 24. Kh1 Bb4 25. Bg3
Bb7 26. Rb3 Qe7 27. Bd3 c5 28. Bb5 Nf8 29. Be5 Ne6 30. f4 Nxd4 31. Bxd4 cxd4
32. f5 Rc8 33. fxg6 hxg6 34. Rbf3 Rc7 35. Qxd4 Qe4 36. Qf6 Rc2 37. Qxf7+ 1-0

Position 3:
Show Solution
In Levitt-Flear, Plymouth 1989, White eventually won after 26. b4? Computers today – and apparently some eagle-eyed kibitzers after the game – spotted 26. Nd8! followed by Qf8+ or Nxe6. There are winning lines such as 26…Qe7 27. Nxe6 g6 28. Bh3 and Qg3.

[Event "BCF-ch"]
[Site "Plymouth ENG"]
[Date "1989.08.??"]
[Round "?"]
[White "Jonathan Levitt"]
[Black "Glenn Flear"]
[Result "1/2-1/2"]
[ECO "D16"]
[PlyCount "59"]
[EventDate "1989.??.??"]

1. d4 d5 2. c4 c6 3. Nf3 Nf6 4. Nc3 dxc4 5. a4 Bg4 6. Ne5 Bh5 7. h3 Na6 8. g4
Bg6 9. Bg2 Nb4 10. O-O Bc2 11. Qd2 Bb3 12. Qf4 h6 13. Be3 e6 14. Ne4 Nbd5 15.
Qf3 Bd6 16. Nxd6+ Qxd6 17. Rac1 Nxe3 18. fxe3 Bxa4 19. h4 Qc7 20. g5 hxg5 21.
hxg5 Nd5 22. e4 Nb6 23. Nxf7 Qh2+ 24. Kf2 Rh4 25. Ke3 Qc7 {[#]} 26. b4 (26. Nd8
Qe7 27. Nxe6 g6 28. Bh3) 26... cxb3 27. Rc5 Nd7 28. e5 Qb6 29. Nd6+ Kd8 30.
Qf8+ 1/2-1/2



In reply to by anonymous_stub (not verified)

In the May issue Test Question 1 shows the Morphy game with a solution of 34.a4 bxa3 e.p. 35.rg7+ Kh8 36.Nf8. But why is this needed as after 35... Re1+ if 36.Kg2 allows the King to get to h3 protected by the pawn on g3? Is the pawn on g3 not supposed to be there? ... or am I not seeing something correctly?

Add new comment

Restricted HTML

  • Allowed HTML tags: <a href hreflang> <em> <strong> <cite> <blockquote cite> <code> <ul type> <ol start type> <li> <dl> <dt> <dd> <h2 id> <h3 id> <h4 id> <h5 id> <h6 id>
  • Lines and paragraphs break automatically.
  • Web page addresses and email addresses turn into links automatically.

Plain Text Comments

Share Your Feedback

We recently completed a website update. If you notice a formatting error on this page, please click here.