Search found 893 matches

by smatovic
Thu Jan 14, 2021 6:18 am
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: From Esoteric to Transcendental Chess Programming?
Replies: 5
Views: 481

Re: From Esoteric to Transcendental Chess Programming?

Interesting, I take this as confirmation that already without NNs in chess 'we'
entered a kind of black-box level (transcendental chess programming) with our
test-driven development methods, thanks.

--
Srdja
by smatovic
Tue Jan 12, 2021 9:09 am
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: From Esoteric to Transcendental Chess Programming?
Replies: 5
Views: 481

From Esoteric to Transcendental Chess Programming?

Heyho, I do not follow SF development, but I get here and there a breadcrumb, for example: "is LVA as in MVV-LVA useless ?" http://talkchess.com/forum3/viewtopic.php?t=70918 "...Lazy SMP feeds on chaos..." http://talkchess.com/forum3/viewtopic.php?f=7&t=72684#p824068 So I ponder if we left the parad...
by smatovic
Tue Dec 08, 2020 11:17 am
Forum: Computer Chess Club: General Topics
Topic: M1 Apple Silicon for Chess?
Replies: 52
Views: 6230

Re: M1 Apple Silicon for Chess?

... Also if the Nvidia-ARM deal doesn't get blocked, the future is RISC-V. Future might be Risc-V regardless but Nvidia-ARM will definitely make risc-v more attractive. I agree, on one side their is a lockdown of Apple ARM and who knows what will happen with ARM+Nvidia, so on the other side is room...
by smatovic
Sun Dec 06, 2020 6:45 am
Forum: Computer Chess Club: General Topics
Topic: Transhuman Chess with NN and RL...
Replies: 6
Views: 1135

Re: Transhuman Chess with NN and RL...

.. The other thing is that the neural networks in recent alpha-beta engines are different from those in Leela or AlphaZero, they are trained with reinforcement learning to predict what the handcrafted evaluation will be in a certain position, rather than the win/draw/lose percentage of the game. An...
by smatovic
Sun Dec 06, 2020 6:21 am
Forum: Computer Chess Club: General Topics
Topic: Transhuman Chess with NN and RL...
Replies: 6
Views: 1135

Re: Transhuman Chess with NN and RL...

... Handcrafted evaluations still have a place in computer chess, if only as an accelerant in neural network training. Training a neural network on a very strong handcrafted evaluation such as the handcrafted evaluations of Stockfish or Komodo will result in a much stronger network than training th...
by smatovic
Fri Dec 04, 2020 6:13 pm
Forum: Computer Chess Club: General Topics
Topic: *** General user warnings ***
Replies: 80
Views: 6219

Re: *** General user warnings ***

... .. In general there is the 'Splinter-Net' going on, Russia, China as forerunners, also India, EU implements its own laws for all kind of platforms, USA? Not sure how this will play out on a global scale for open platforms. ***edit** TalkChess with ~2800 registered members is IMO at the border-l...
by smatovic
Thu Dec 03, 2020 1:44 pm
Forum: Computer Chess Club: General Topics
Topic: *** General user warnings ***
Replies: 80
Views: 6219

Re: *** General user warnings ***

Not sure, maybe people do not get the technical part, TC is side hosted (for free) on the ChessUSA shop server, the shop suffers now and then from hacking- attacks and therefore blocks whole IP ranges, this then affects also TC, and users from different regions can not access the website. I think Ch...
by smatovic
Fri Nov 20, 2020 6:52 am
Forum: Computer Chess Club: General Topics
Topic: GPU rumors 2020
Replies: 38
Views: 13485

Re: GPU rumors 2020

... Beast without framework is a joke. AMD's pathetic attempts to go into ML market are pretty pointless. Well good luck to them with OpenCl. Btw. in 7nm having best performance in BFLOAT16 of 0.5TOPS/W is pathetic. This coming from someone actually designing HPC AI hardware. Nvidia invested early ...
by smatovic
Fri Nov 20, 2020 5:25 am
Forum: Computer Chess Club: General Topics
Topic: GPU rumors 2020
Replies: 38
Views: 13485

Re: GPU rumors 2020

... Beast without framework is a joke. AMD's pathetic attempts to go into ML market are pretty pointless. Well good luck to them with OpenCl. Btw. in 7nm having best performance in BFLOAT16 of 0.5TOPS/W is pathetic. This coming from someone actually designing HPC AI hardware. Nvidia invested early ...
by smatovic
Fri Nov 20, 2020 5:01 am
Forum: Computer Chess Club: General Topics
Topic: GPU rumors 2020
Replies: 38
Views: 13485

Re: GPU rumors 2020

I wonder how the AMD MI100 compares to the Nvidia A100: https://nvidianews.nvidia.com/news/nvidia-doubles-down-announces-a100-80gb-gpu-supercharging-worlds-most-powerful-gpu-for-ai-supercomputing?mkt_tok=eyJpIjoiWXpVeE9XVTRNak00TmpjMCIsInQiOiJqSVFpWDJCelBZdHc3U1BBRHl6ZGxDQXc3dkc4NllkM3pwQ0xScmkrOTE...