I've been using ChatGPT since launch and constantly seeking out examples of how others have been using it. A few years ago I started using KataGo with Sabaki to improve my go-playing abilities. I've known about token embeddings in neural networks before ChatGPT was a twinkle in OpenAI's eye. I was there, but I haven't seen everything you've seen, so please show me. If the truth is that ChatGPT has canned responses... Source: about 1 year ago

It's a feature with sabaki, to make it look resemble a real board more. Source: over 1 year ago

That said, if you can download some sgfs and view them in a tool like [sabaki]((https://sabaki.yichuanshen.de/), you can try and match the score that the computer reports. You can get SGFs from here - other sources are available. Be sure to find games which were won on points. You can't count a game won by resignation. Source: over 1 year ago

It's a shame because KGS would benefit greatly from a modern client. I think at this point writing a new client from scratch would be preferable, or maybe taking something like [Sabaki](https://sabaki.yichuanshen.de/) and turning it into a KGS client might be viable. Speaking of which, Sabaki is a good option for those looking to contribute to an open source project. Source: over 1 year ago

You can also just download pre-trained models. Get those set up and then install Sabaki (https://sabaki.yichuanshen.de/) and connect it to your KataGo... Instant (ok, a few hours probably if it's your first time setting it up) superhuman Go AI. There's even an npm package you can use to process SGF files and automatically score moves as good/questionable/bad + generate variations that were better choices:... - Source: Hacker News / over 2 years ago

OpenAI Gym: If you're interested in using AI for machine learning, OpenAI Gym (https://gym.openai.com/) is a great resource. It's a platform that provides a wide range of environments and tools for developing and testing machine learning algorithms. You can use it to experiment with different techniques and see how well they perform. Source: over 1 year ago

Open source toolkits such as Open AI Gym can be used for developing and comparing reinforcement learning algorithms. - Source: dev.to / about 2 years ago

There is a lot of work in games, particularly board games, but these do not really solve something "useful" for society. I have seen also lots of toy examples with libraries like gym and some robotics but in general these are rather proof-of-concept models or just models that do not work at all. One that actually does work is Solving Rubik’s Cube with a Robot Hand. This is pretty cool, but again, the domain... Source: about 2 years ago

I haven't used it, but assume https://gym.openai.com/ is exactly for this. Source: about 2 years ago

I know it's not a good website but I thought https://gym.openai.com/ was the documentation, is it not? Source: over 2 years ago