Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Advice from ChatGPT #2

Open
TheIttyBittyGalaxy opened this issue Jan 21, 2023 · 0 comments
Open

Advice from ChatGPT #2

TheIttyBittyGalaxy opened this issue Jan 21, 2023 · 0 comments

Comments

@TheIttyBittyGalaxy
Copy link
Owner

Just for giggles, I asked ChatGPT for some advice on the language. Terrifyingly, I thought it's response was actually quite helpful! So I figured I'd make a note of it here.

Me

I am also working on another programming language called Gambit. It is a programming language for board games where you write the game rules, then the compiler gives you a playable executable with a built in Monte Carlo Tree Search AI. What might be a good way for me to explain the language to people who don't know about it?

ChatGPT

One possible way to explain the Gambit programming language is to start by describing the problem it aims to solve: the difficulty of creating an AI for board games. You could explain how traditional methods for creating AI for board games can be complex and time-consuming, and how Gambit simplifies the process by allowing developers to write the game rules in a simple, high-level language and then automatically generating an AI that uses Monte Carlo Tree Search.

You could also talk about the benefits of using Monte Carlo Tree Search, such as its ability to handle imperfect information and make decisions in real-time. Additionally, you could highlight the key features of Gambit, such as its support for a wide range of board games, the built-in visualization tools to help developers understand the AI's decision-making process, and the ability to easily test and iterate on the AI's performance.

It might also be useful to give some examples of the kind of board games that can be created using Gambit, such as chess, Go, and other strategy games. You could also show some code snippets to illustrate how easy it is to write the game rules and create an AI using the language.

Finally, you could mention the development status of the Gambit, whether it's in alpha, beta or a stable version, and invite people to try it out, provide feedback and contribute to the development.

Overall, the key is to clearly explain the problem that Gambit solves, the benefits of using Monte Carlo Tree Search and the ease of use of the language and its features.

Me

Can you write an example description?

ChatGPT

Sure, here's an example of how you might describe the Gambit programming language:

"Gambit is a new programming language for board game developers that makes it easy to create powerful and intelligent AI opponents. With Gambit, you can write the rules of your game in a simple, high-level language, and the compiler will automatically generate an AI that uses Monte Carlo Tree Search to make decisions.

Monte Carlo Tree Search is a powerful algorithm that can handle imperfect information and make decisions in real-time, making it perfect for board games. Gambit also includes built-in visualization tools to help you understand the AI's decision-making process and test its performance.

Gambit is versatile and supports a wide range of board games, from classic strategy games like chess and Go to more complex games with unique rules. The language is also designed to be easy to learn and use, making it accessible for developers of all skill levels.

Gambit is still in development, but you can try it out, provide feedback and contribute to the development. With Gambit, you can create intelligent and challenging AI opponents for your board games without the complexity of traditional AI development methods."

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant