I’ve also been experimenting with Chess and LLMs but have taken a slightly different approach. Rather than using the LLM as an opponent, I’ve implemented it as a chess tutor to provide feedback on both the user’s and the bot’s moves throughout the game.
The responses vary with the user’s chess level; some find the feedback useful, while others do not. To address this, I’ve integrated a like, dislike, and request new feedback feature into the app, allowing users to actively seek better feedback.
Btw, different from OP's setup, I opted to input the FEN of the current board and the subsequent move in standard algebraic notation to request feedback, as I found these inputs to be clearer for the LLM compared to giving the PGN of the game.
I am a long-time lurker here, and I need your help to get out of my own matrix. I promise it will help you get out of your own matrix as well. Just have faith in our oldest sport before computers: philosophy. I am sure you will like it, so I tried to deliver. Your comments are valuable, so don't hesitate to shoot any questions. I will be here to explain everything. Please try to find specific loopholes rather than dismissing the story as a myth. We all know that we are living in myths, as Snowden had to sacrifice himself for this knowledge. Please honor his and my loyalty to the survival of Gaia.
It is a blog written by a fictional alien who is amazed by our evolution. Due to that, it is trying to help us understand the intrinsic motive of evolution and everything else. It is also talking about its own 'weird' evolutionary path for comparison.
I am trying to give an out-of-the-box view on what I have learned as a frequent reader and amateur thinker on these topics. However, I didn't attempt to write something like this before. It may have a lot of structural errors. Also, I am not a native speaker (which might suit the role-playing though)
I remembered the article[1] talking about data as its own being, even maybe a separate consciousness. And, then I thought a story dated back that many years should be, arguably, the oldest preserved data that the intelligent life on earth ever had so far. I am excluding the language itself, of course.
So, this makes it the most ancient branch of Dataome. It is quite cool to observe the baby steps of the next evolutionary path.
The responses vary with the user’s chess level; some find the feedback useful, while others do not. To address this, I’ve integrated a like, dislike, and request new feedback feature into the app, allowing users to actively seek better feedback.
Btw, different from OP's setup, I opted to input the FEN of the current board and the subsequent move in standard algebraic notation to request feedback, as I found these inputs to be clearer for the LLM compared to giving the PGN of the game.
AI Chess GPT https://apps.apple.com/tr/app/ai-chess-gpt/id6476107978 https://play.google.com/store/apps/details?id=net.padma.app....
Thanks