David J Wu

Thanks. I think I see the issue. At the time of the warning, the parameters actually haven't been read and used yet, so it thinks it needs to warn about...

I made the fix to the code that will go into an upcoming release (https://github.com/lightvector/KataGo/commit/7ba9e93ba23f036d43014c7e9eb1375e3ebbf5d0), thanks again for reporting. While working on the fix, I did realize there is one...

This is excellent, thank you! Please keep posting more variations with major errors if you find them, I can use them to expand the book and this will likely correct...

Even if Leela Chess Zero does it, my recollection was that it is still clearly against nvidia terms of service to do so.

Where did you point it out before, and do you have an SGF for this and the other cases? If there is very systematic or repeated type of shape that...

Thanks! Are there any other games you know of with a similar problem, or is it only this game so far? How do we tell the difference between "all the...

Of course, I haven't added this position as a training position. It probably will remain unchanged in this position for a very long time unless the neural net starts to...

Sorry, yes perhaps I misworded things in a dismissive way. Yes, even if a blind spot only occurs in this single game position, it was still impactful to to the...

For example, in an earlier post, you suggest > Add a small set of loose-ladder failure positions as part of a possible experiment / testing. Do you think you'd be...

> **Proposal: add a small policy floor** Assign every legal move a minimum prior of ε = 0.1 %, then renormalize (e.g. `P = max(P, ε); renorm()`). > > **Why...