Running a Chess YouTube Channel entirely by AI — Stephan Steinfurt, TNG

Hello everyone. Um, yeah, Swix wrote a blog post and said, "Okay, don't write boring titles," so I changed my title again, actually. And said, okay, we're wo- working on the holy grail of chess programming. And if you knew me, I mean, I'm usually not the kind of guy who oversells stuff.

So it's actually a quote from someone else, uh, about this. Because, like, roughly a week ago there was an article on one of the biggest newspapers in Germany, which was, um, discussed a couple of approaches to, yeah, new approaches to doing, yeah, combining AI with chess.

And yeah, they had said, um, it could easily take another 5 years until AI explains chess as well as a human trainer. Würdemberger calls it the holy grail of chess programming, and work is already underway in Munich, and that's basically where we are from,right.

And we showed them a couple of videos, um, that my bosses mentioned, and myself, and yeah, they were completely created by our AI engine. And I want to quickly tell you a little bit how that's, uh, working. So maybe, um, you don't want to only show it to the newspaper, but also show it to you.

There's a 2-minute video of what the outcome is. So I'm going to start it now.

In this position, black's queen is currently under fire from the white rook on the h-file. Trying to find safety, black slides the queen over to g4. This is a crushing blunder. It looks like a completely safe square, but moving off the h-file allows white to unleash a spectacular, mind-bending sacrifice.

White plays rook takes h5. Huh, white is offering up a full exchange, but this is a masterful trap built on incredible knight geometry. Let's look at what happens if black takes the bait. First, if black simply recaptures with the g-pawn taking on h5, white springs the trap.

The knight jumps into the action with Nf6 with check. Heh, look at this beautiful octopus knight on f6. It hits the king on g8 while simultaneously skewering that newly placed queen on g4. A lethal fork. The king is forced to step aside to f8, and the knight simply scoops up the queen on g4.

But wait, let's back up. What if black tries to be clever and avoids the pawn capture? Black could capture the rook with the queen, playing Qxh5. But it is the exact same trap. The queen is attractedright into the danger zone.

By pulling the queen to h5, white set up the exact same trick and plays Nf6+ anyway. Once again, the king is attacked, and the knight reaches across the board to attack the queen on h5. Heh, no matter how black captures the sacrificed rook, the queen gets forked, because this knight magically controls both g4 and h5.

The king must step aside to f8, and the knight captures the queen on h5. This is a gorgeous double-duty fork, demonstrating the terrifying hidden power of the knight. Always watch out for these tricky jumping pieces when your king is exposed.

So actually, when I prepared the talk yesterday, I, um, I wanted to show a different vi- video, but, um, yeah, we're, um, automatically creating these videos every, every night and uploading them to YouTube. And when I this morning had a quick look if there's anything embarrassing there, which I could, should hide, hide from all of you, I thought, okay, actually there's this video, and it's actually even better than the other one, so I might go for that one.

And, uh, yeah, as I said, it's automatically created. Um, we, um, basically download, um, yeah, chess games from LeChess every, every night and analyze them in the background, and then let our agent run and analyze it in more depth.

From that analysis, we then create some special format with, from which we can later on then create a video. And yeah, the video in the end shows variations being explained. It shows brilliant moves, uh, blunders, and yeah, and it's all, uh, automated.

And, um, yeah, so how does it work? So maybe backing up a little bit. What's the general problem? The problem is we've had really good chess engines for multiple, yeah, decades, actually, and but they can't really explain chess well.

On the other hand, we have now LLMs. They can, well, say, um, have words and, uh, describe things, but they can't play chess well. So we have to somehow combine them. That's the main challenge. And yeah, we are now have built an agent which, um, has a lot of tools, which is basically the, um, main, uh, yeah, important ingredient here.

But, um, what is also important is the LLM which we're using under the hood. So Gemini 3.1 Pro, which recently came out, is actually like the best model I've seen so far on, on chess. I'm pretty sure they've di-did some, done some, yeah, yeah, uh, in-depth post-training on the model, and you can really see in the reasoning traces that it really understands chess a lot better than the previous models.

Um, but what we have now put on top of that particular model is a list of tools. So what have we got? Um, we have got a tool for legal moves, um, yeah, to just prevent it from ever, like, thinking about something completely illegal,right, on a chessboard, which might otherwise happen.

Then we basically give the agent a complete chessboard and let it play moves and take them back and, uh, go to various, um, variations itself. It can then always run a chess engine and, um, yeah, also have get some other kind of chess data, for example, looking at checks, captures, and threats.

And yeah, for some kind of videos, we also include web search because then it might be interesting to also describe the historic context of a game or something like that. So looking at one particular tool in, in detail, there's the checks, captures, and threats tool.

Um, that's actually quite well known in chess as a, like a, like a beginner's explanation, um, of what you should be focusing on if you've got a, um, position. So this is a relatively complicated position in which, um, I'm guessing not that many people in the audience would immediately know which one is the best move.

I mean, does, does anyone want to have a guess at it? No. I mean, it's, it's pretty complicated, to be honest. It's a tile game. Um, but what we're giving the, the LLM now in this situation is not only the best move, but we're giving it also access to checks, captures, and threats, because it otherwise might, might miss that.

And you can see that there are a couple of check moves, um, yeah, on the left board, um, some of which are obviously wrong. So like, for example, with a queen taking the bishop on, on a4 is obviously a bad move.

Um, some other queen moves to give a check, they are quite reasonable. But actually, the best move in this whole situation is to sacrifice the rook on e3, which is not completely obvious here, but that's actually the best move.

In other situations, it might be, however, much better to look at the check, uh, of the, at the capture moves. And, um, by providing all this via one tool, we give quite some diversity to the agent to, um, then maybe, maybe later on explore other kinds of, um, variations.

So maybe it wants to check all of these moves and, and, uh, yeah, describe which ones are actually bad because a human might think about them. And it, so it's not always about the very, very best move, which we have to describe.

Um, in general, the big question is who should do the thinking. So when we started this whole project, we initially had a, like, some Python scripts which would analyze a chess position and would then assemble information from various, um, positions and would say, okay, here are the, the check moves, and that's the engine evaluation.

And then we would then pass it on to the, um, language model to then have a whole description. But what, um, changed last year when reasoning models came out was actually that the, the agents could, um, yeah, rather think themselves about the, the positions.

And they were already pretty good. So, um, the best model which we've been using, like, in, in, in autumn last year was Grok 4, surprisingly. That was sort of the best one. But, um, yeah, also the other models, like from OpenAI and so on, they also, um, have quite some decent, uh, base chess knowledge to be able to then call the tools at theright position and then, yeah, like assemble all the knowledge.

And yeah, as I already mentioned, this kind of conflicting information which we provide via the tools is actually very beneficial. So, um, we also have, um, other kind of tools which more, more geared towards, um, yeah, having, um, getting out the more human moves and positions.

And yeah, that also helps to balance the, um, the description of not being too much focused on the best moves, but also, like, on the most human moves. Also, in the historical context, there might be, uh, like some valuable information, um, which moves have actually been played or someone might have described something in, in detail which we might want to analyze.

So all these kind of things, um, get into the mix in the context. Yeah, after we did the whole analysis, we would then create it into a special format which we could then easily transfer into, uh, um, yeah, into a video.

Um, we then use 11Labs v3 for text-to-speech. Yeah, it's actually pretty, pretty nice that there are now also these audio tags, like, uh, you can put this "excited" in there and it would then sound excited. And yeah, and also, the agent also decides by itself which squares it wants to highlight, which arrows it wants to draw, and if something should be considered a brilliant move or not.

Yeah, and now maybe also some other questions. So is that all slop what we are, what we are creating? I think not, obviously. Um, but yeah, I mean, we are able to create many, many, many such videos. So we have to really balance of how much do we want to put out there on YouTube.

So, um, what is the input? I mean, the input is actually human games. So in a, in a sense, um, what we are now positioned at is we could be creating videos of your games, and you could send the videos then to your friends and family.

And, um, we are not trying to, um, I don't know, put in these artificial things like exploding position, uh, like, uh, exploding kings or something like that on check, checkmate, which might, might be beneficial for the view count and so on.

But we are really trying to, uh, yeah, get the most out of the chess quality. Uh, in general, why are we doing this? I mean, there are a lot of interesting and great streamers. So for example, GothamChess is one, one is maybe the, the, uh, yeah, most well-known streamer.

But they, he would probably not, um, describe one of your games or my games, uh, in his videos. But we now have a, a way to also scale for other people who are not like the best players in the world and who might, which, um, yeah, might also like to have a video.

And yeah, we've got a YouTube channel and, um, yeah, currently it's like something like 500k views. And yeah, more than 4,000 subscribers. Most of them actually were, um, yeah, subscribed within the last month. So it's actually going up quite a bit there.

Yeah, and that's it. If you've got any more questions, I mean, ask them or send me a message via these platforms here, whatever. And yeah, that's it.

Yeah.

Uh, how, how, what, what are the costs that you monetizing YouTube channels? Is it like covering the LLM influence costs yet?

Well, currently, we don't make any money yet because we're not, haven't reached the monetization stage yet. And so it's net minus at the moment. But okay, it might change. We'll see.

So you self-verifying the videos before you put them up, like how many videos are you generating and how many, like, be-be-be quality benefits?

Yeah, I mean, so, um, this whole, uh, automation, we only, like, enabled like a couple of weeks ago. And so currently, I'm still like a little bit skeptic. Should I really, like, just leave it, uh, upload videos? And yeah, I'm mostly still leaning on, okay, I still want to watch them first ones.

But, um, yeah, the error rate is actually pretty low. So I would say every 20th, um, video maybe has a, a very weird description in which there's, I don't know, a checkmate, uh, and, uh, that's missed or something like that.

But I mean, that's usually also then of, uh, valuable information,right? Because maybe some, like one tool call was not done at the very end, and okay, we can learn something from that. But I've actually much more now switched to, okay, I don't care anymore.

And even if there's a bad video, then I'll take it down afterwards, maybe. Yeah.

Anything else? Yeah.

What is the, what's the cost of a video?

Um, it's, um, something on the order of, yeah, 20, 30 cents, something like that. So I mean, we also have created a couple of other videos which are like, uh, much, much longer, and there it can also get to euros and something like that.

Um, currently, we are not trying to optimize the costs too much because, um, uh, we rather want to err, err on having a too-good description, sort of. And but there are also a couple of optimization possibilities in there, I don't know, redundant tool calls.

Sometimes the agent goes through a game like twice or something like that. And yeah, that's obviously stupid in a sense.

Yeah.

You were talking about, um, human move. Is it like grandmaster human move or like beginner, uh, human move that you might put in the mix?

Yeah, basically all. I mean, so there's this, this, um, uh, Maya engine, which was also mentioned, uh, uh, yesterday in the talk. So, um, by the University of Toronto, which, um, yeah, they trained a model in which you can basically, uh, put a, yeah, rating of, uh, of a player, and then it would roughly, um, give you, uh, a move which that player might want to play.

But it's not like it, I mean, it's not like perfect in that sense,right? But it still might be valuable information that maybe some move like this, uh, deserves a description. So we don't necessarily need to have what really a human would be playing of that strength, but rather like a mix of different things to consider.

So it's to explain like a so-called learning.

Yes, exactly.

Like 160 hello or, you know, something, someone that doesn't play super well yet.

Yeah.

You want to explain to.

Yes. I mean, these, these things could also be used then for targeting a little bit more like for the audience, rather have like videos for, for better players or videos for worse players. And, um, I mean, currently, uh, we are also not really sure exactly how, uh, which videos we should be putting up there or not.

I mean, sometimes we also have videos with a checkmate in one, which for like good players is sort of ridiculous. I mean, you see it immediately. But on the other hand, there, there, there are real beginners who really don't see that and need also an explanation, uh, why that's a checkmate and so on.

So yeah, it's, it's all a bit of a balancing question which we are not really sure yet. Yeah.

Have you tried other games?

No, not yet. But yeah, I mean, it's sort of, uh, possible to extend in a sense. Yeah.

Okay. Yeah, then that's it. Thanks.