michito744
michito744
As indicated by the ratings, kata1-b60c320-s6321537280-d2951683615 is a very well balanced and powerful network. It withstands very deep searches better than any network in the past, with more accurate predictions...
A phase that has been covered in past issue. It is very very cheep...  With a little assistance, KataGo can reach the right conclusion, but...  The weighting...
Incredible oversights occured in the following situations:     It's definitely stronger than it used to be, but it's definitely a failure to get rid...
I usually make a lot of hard requests, but I would like to report that the combination of the latest 60b and TensorRT versions is good for "searching long straight...
The following figure shows a wonderful search path that could never have been reached in the previous version. (Although in the actual game move-3 is D6 and move-4 is D8,...
This is a procedure that the zero-based-AI completely overlooked in a phase that appeared in a recent actual game.  The black player, Yu pro, had discovered the procedure...
There is a example of cases where a wrong conclusion is reached by choosing a clearly ludicrous progression in 28b, when it could resolve in 18b. #796  ...
From #956 The latest version of the b28 network is extremely good and has accurately and quickly resolved many of the aspects we have addressed in past Issues. Therefore, paradoxically,...
This is the phase where KataGo made the worst mistake by failing to search a mere 30~40 moves. Incidentally, FineArt also failed to come to the correct conclusion, so this...
A problem that AI cannot solve at all, which arose in a professional real-life situation.   This is due to the inability to effectively solve loose ladders—a long-standing issue...