2 open projects

[jp]

... I wonder by how much can the NN be increased before the the decrease in nps will cause overall negative elo gain. Even if one could run every NN in constant time (independent of NN size) there is probably diminishing elo gain by doubling the NN size, so there will be some finite limit even for infinite sum of NN doublings.

I am also wondering if there are any other NN architectures that are being considered that could go beyond what just scaling of current architecture can achieve.

Yes, good questions. I think the first task is to work up to & establish a benchmark with a 20x256 NN, because right now we don't really know what that benchmark (true chess strength) is.

[Albert Silver]

Silver said in that keynote talk that they did multiple runs, and I'm pretty sure they didn't publish the results of a run where they had the sorts of bugs the Leela project has had so far

There's very little point idly speculating about what can and can't be achieved by the project.

Time will tell.

Are you referring to the paper, or is there a talk you can link to?

[syzygy]

Silver said in that keynote talk that they did multiple runs, and I'm pretty sure they didn't publish the results of a run where they had the sorts of bugs the Leela project has had so far

There's very little point idly speculating about what can and can't be achieved by the project.

Time will tell.

Are you referring to the paper, or is there a talk you can link to?

Probably this:
https://www.youtube.com/watch?v=Wujy7OzvdJk

[Albert Silver]

Silver said in that keynote talk that they did multiple runs, and I'm pretty sure they didn't publish the results of a run where they had the sorts of bugs the Leela project has had so far

There's very little point idly speculating about what can and can't be achieved by the project.

Time will tell.

Are you referring to the paper, or is there a talk you can link to?

Probably this:
https://www.youtube.com/watch?v=Wujy7OzvdJk

Thanks!