apleasantillusion

Interestingly, on the Rc7?? Kxc7 and Ra6 Kxa6?? blunders above, I can reproduce them with ID288 on CPU both with game history. With just FEN, while it doesn't play both...

In the game nelsongribeiro posted, the same pattern holds true (tested with 292). With history, she plays 124.Ke7 with a very high probability from policy (84.89%), and the response Qxd5...

Just to add to this, the Rxf3+ that's being tracked in the sheet at https://docs.google.com/spreadsheets/d/1884-iHTzR73AgFm19YYymg2yKnwhtHdaGyHLVnffLag/edit#gid=0 shows the same behavior. With net 297, probability with various 50-move counter rule values: 0:...

These both seem to be fairly innocent problems. In the first game, Bd4 has a really low probability from the policy head, so takes a while to be searched. Once...