OOTP and AI

[sixto]

One of the things that I think has always been a strength of Markus and OOTP has been an eagerness to be an early adopter. FaceGen being a great example of a new technology that was incorporated into the game early and in an innovative way. BABIP another, flawed though it may have been — that kind of adaptability is in OOTP's blood.

I believe the OOTP ethos will be an asset as AI makes its way into game development. Here are 9 ways that I think AI could be utilized in the very near future to take OOTP leaps and bounds beyond where it is today. Licensing costs for the technology not considered!

1. Logo and Uniform Creation. I'm guessing anyone who has played OOTP has dabbled with AI and logo creation. AI gets better at it every day, and I'm sure this will be a part of OOTP sooner rather than later.

2. Player photos and identities. AI (and many graphics engines) have advanced so far in this area. AI can not only create a face, but also readily create photo effects to make the image look the proper vintage. 19th century players in grainy black and white? 60s players in fuzzy color? What AI can do would have to be adapted to the OOTP game engine, but the possibilities are literally endless.

3. Ballparks. If you're like me you've also asked AI image generators to create baseball stadiums by now. Me, I like photorealistic, but you may want a ballpark in Mordor or on the edge of a waterfall. How long before what AI can do is merged with what OOTP can do? I'm guessing not as long as one might think. Create-a-Stadium is sort of stuck in neutral at the moment — no one has created new modules for use in the game. A whole new level of innovation might be the answer.

4. Player creation and development. Imagine being able to type into OOTP, "Create a new free agent, age 20, similar to Cal Ripken, but a catcher with a great arm, great framing and no speed." Training AI to convert instructions into player data should not be especially difficult. We'll have to be protected from ourselves of course so that we don't create impossible freaks of nature.

AI probably also already understands the way that players typically develop as well if not better than any human mind, having been fed all the statistics by now. There will be a time when games like OOTP don't have to rely on fragile algorithmic estimations of how players age. And give AI license to deviate from expectation a certain amount of the time, and watch out! AI will be able to create Brady Andersons and Jose Bautistas far more readily than any algorithm.

5. AI-generated sound effects. Crowd noise, the crack of the bat, the seventh-inning stretch. I realize that not that many people actually play games out one by one, which is a real shame — IMO, it's the most fun way to play. That said, the sounds are limited, repetitious, and at times, not quite appropriate for the situation. AI is already adept at creating ambient sounds. When this kind of technology is adopted into OOTP, it will become a mode of play that I think more people will feel compelled to explore.

6. Original radio broadcasts. Along the same theme: AI has presumably been trained at this point (legally or not so legally) on who knows how many baseball broadcasts. The nuts and bolts, the banter, even the promo spots — AI will be able to do them all, maybe can do them all already.

It's an ethical gray area whether to try to use AI to faithfully re-create the vocals of real life people, alive or dead. But as much as I would love to hear Vin Scully or Harry Kalas broadcast just one more game, I don't think that's necessarily the right road to go down. OOTP could instead use what AI knows about how announcers of different eras have sounded to create, or allow us to create, original baseball broadcasters that violate no IP laws nor tread indecently on anyone's memory, and enable us to listen to baseball games featuring whichever stars and teams we'd like to hear. This one is probably further down the road than the first five, but it's one to wish for, in my book.

7. AI. Lol, of course! AI will at some point, probably not too far from now, be integrated into the AI managers and general managers and owners of OOTP. Realistic dialogue with an AI GM about a trade you want to propose? It will happen some day. I don't know when. It's really exciting to think about, especially if you are old like me and have been playing baseball sims for almost 40 years.

8. News generation. AI can already write sports articles as well as just about any stringer. Adding the basics like game summaries would probably be fairly simple to implement. An all-out media ecosystem generating trade rumors, prospect scouting reports and feature stories custom made for each league market will be possible, but also potentially overwhelming. Still, AI has so much potential here, and in Football Manager for that matter, to really step up to incredible levels of detail and immersion.

9. Play results. What a chore it must have been to have to program into the game hundreds of different game outcomes and then program the game to illustrate those outcomes in a watchable way. And the method has limitations, like the game not always knowing or understanding how far away the fences are, or how that plays into park effects. But here comes AI, able to be given a 3D picture of a baseball stadium made up of thousands (millions?) of coordinates, and being tasked with figuring out where a pitched or batted ball will fly, how far it will go, how much humidity and wind affects it, and what it all looks like when it happens. AI could generate results that are exactly like the results of a real game. It isn't even about letting AI decide the actual outcomes — for a while, that may still need to be programmed by a human. But in terms of how that is rendered in the game engine, AI should be able to help sooner rather than later.

I could go on all day. Thanks for reading that much. Really excited to see how AI helps turn OOTP into the game of (beyond) our dreams.

[Syd Thrift]

Long time no see from an old school OOTPer, which is why it pains me to be the person who has to respond to this with...

Not only no but heeeeeeeeeell no. For most of the things that would "work", LLMs really aren't "AI" in the sense of there being some, like, actual, like "soul" that's actually taking in data and making writing decisions. It's much more like a giant game of Mad Libs in which the AI scours its database for data it more or less stole from people who actually did creative work and then randomly pops it in. I'm sorry if that makes me sound old or something but this is pretty much all LLMs do.

I think that if anything LLMs will get worse at this in the future, not better, because many places are already beginning to limit what data they have access to and so it's left with mostly pulling stuff from the public domain or else using whichever proprietary data it can get its hands on. That's not my primary issue with using LLMs, of course (see above) but I think when you're faced with a thing that's at least morally grey and stands a chance to not be as good as currently is in 5 years (and let's be honest, AI right now reads like freshman-in-HS writing assignments; I wouldn't even put them at "stringer" level), it should give you pause.

I'm a little bit less against using neural networks to develop AI but if I'm being honest I don't think that's going to do what you think it's going to do. AI is more or less the best at taking some situation with a relatively small number of inputs, doing what amounts to random crap along the thing it's allowed to influence, and then, after being told which approaches are successful and which are not, to come up with "better" solutions until it reaches something that is in some way, according to the metrics you're using to define success, etc., to find "optimal".

That's just not at all how managers and GMs think, for better or for worse. To be honest, this is for better in many ways: no real-life manager would ever hit their pitcher leadoff but an AI is liable to try it unless you tell it not to. On the other hand, managers and GMs primarily make moves with a mind of not getting fired and so if you train an AI based on, say, a 5 year rolling average of wins and losses, it might come up with some really, really non-traditional baseball moves. This might seem like fun in the abstract but when you're, like, trying to play a game that you want to feel like "real" baseball and like the White Sox are putting their pitcher in the lineup and hitting him cleanup because that helps them tank better in Year One, for example, you're not going to walk away from that with a good feeling.

And that's even something that does make sense if you think about it. What if the AI "figures out" something that actually works in baseball but is just plain never used IRL? You can say "hey, the AI figured out that a 6 man rotation where the starters go 3 innings is the most optimal and also that LOOGYs are the most valuable commodity in the game so it signs them to $30M a year contracts" all you want, but that doesn't feel like *baseball*. Worse, what if those "baseball" exploits the AI uncovers are actually just OOTP exploits? I guess on one level if gives the developers potentially valuable information in terms of loopholes to close. On the other, you aren't going to release that AI to the public, at least not after you've closed that particular loophole. What if the AI finds a thing that's like 0.04% more efficient than what's done IRL - or even only just as efficient but since that particular behavior isn't directly harmful it doesn't get "succes rate"-ed out but just isn't done for good or for bad reasons?

Again I think using neural networks to figure out AI is probably the most morally acceptable use. That doesn't actually make it a good idea.

[sixto]

Some interesting points for sure! And a helpful post because I can respond to your points and illustrate better what I mean.

I don't think AI will be incorporated into OOTP (or many other games) as open-ended LLM projects. Rather, what I see developers doing is taking and compartmentalizing a proven AI capability, and then incorporating it as is, without any further development (until, perhaps, the next release).

So, take each of my bullet points, and imagine what AI will be capable of doing on Day X. Say, Feb. 21, 2025. Whatever that capability is — let's say at making logos — can be made part of the game, at which point the development of that AI will be frozen until it is updated. The AI will no longer "learn," but will simply be able to do what it could do when the game build was released. You tell it, "Make logos, but just make them like this or this or this (like you know how) and just make them sharp and cool."

Or take AI-generated crowd noise. AI can already simulate crowd noise, or a ball slapping a mitt. So you give the game little subroutines where it uses the knowledge it already has to make these noises, and it can only get as sophisticated as the programmer allows. In the game, it's not going to learn as it goes, but it can apply what it already knows. In that way, the developer maintains the same sort of control over the simulation that the developer has always had.

That's how I see all of these aspects of the game being impacted by AI — any game really — with the developers taking advantage of what amount to coding cheats that machines have learned how to do.

I completely agree that no one wants a rogue AI general manager who appears to be trying to make decisions like a human. The results would be too unpredictable, as you point out. Not sure when AI will be capable of that, but it's not part of my vision anyway, probably because I too am an old guy.

[Ilove_Telin54]

imagine it have tool of ai for ootp?

[Canary85]

i would stop buying ootp if they implemented ai/llm into the game like this.