RPG Evolution: The AI DM in Action

How might WOTC launch an AI-powered DM assistant?

Picture courtesy of Pixabay.​

We know Wizards of the Coast is tinkering with Artificial Intelligence (AI)-powered tools for its multiple properties, including Dungeons & Dragons. But what might that look like in practice?

Interactive NPCs​

Large Language Model (LLM) AIs have been used extensively to create non-player characters of all stripes on Character.AI. It's not a stretch to imagine that Wizards might have official NPCs included as part of the digital purchase of an adventure, with the rough outline of the NPC acting as parameters for how it would interact. DMs might be able to create their own or modify existing NPCs so that the character drops hints or communicates in a certain way. Log outputs could then be available for DMs to use later.

There are several places today where you can create NPC bots powered by AI that are publicly available, although the DM might need to monitor the output in real time to record the conversation. Character.AI and Poe.com both provide the ability to create publicly available characters that players can interact with .

Random Generators​

There are already dozens of these in existence. What's particularly of note is that AI can go deep -- not just randomize what book is in a library, but provide snippets of text of what's in that book. Not just detail the name of a forgotten magic item, but provide stats for the item. For WOTC products, this could easily cover details that no print product can possibly encompass in detail, or with parameters (for example, only a library with books on necromancy).

AI RPG companion is a great example of this, but there are many more.

Tabletop Assistants​

Hasbro recently partnered with Xplored, with the goal of developing a "new tabletop platform that integrates digital and physical play." Of particular note is how Xplore's technology works: its system "intelligently resolves rules and character behaviors, and provides innovative gameplay, new scenarios and ever-changing storytelling events. The technology allows players to learn by playing with no rulebook needed, save games to resume later, enables remote gameplay, and offers features like immersive contextual sound and connected dice."

If that sounds like it could be used to enhance an in-person Dungeons & Dragons game, Xplored is already on that path with Teburu, a digital board game platform that uses "smart-sensing technology, AI, and dynamic multimedia." Xplored's AI platform could keep track of miniatures on a table, dice rolls, and even the status of your character sheet, all managed invisibly and remotely by an AI behind the scenes and communicating with the (human) DM.

Dungeon Master​

And then there's the most challenging aspect of play that WOTC struggles with to this day: having enough Dungeon Masters to support a group. Wizards could exclusively license these automated DMs, who would have all the materials necessary to run a game. Some adventures would be easier for an AI DM to run than others -- straightforward dungeon crawls necessarily limit player agency and ensure the AI can run it within parameters, while a social setting could easily confuse it.

Developers are already pushing this model with various levels of success. For an example, see AI Realm.

What's Next?​

If Hasbro's current CEO and former WOTC CEO Chris Cocks is serious about AI, this is just a hint at what's possible. If the past battles over virtual tabletops are any indication, WOTC will likely take a twofold approach: ensure it's AI is well-versed in how it engages with adventures, and defend its branded properties against rival AI platforms that do the same thing. As Cocks pointed out in a recent interview, WOTC's advantage isn't in the technology itself but in its licenses, and it will likely all have a home on D&D Beyond. Get ready!

 

[Sulicius]

We're not talking about the same kind of 'controversial'. To say that an argument assumes as its foundation a controversial premise is really just a nice way to say they're begging the question.

No one who is anti-AI would consider AI art to actually be art regardless of its appearance.

Sure, I agree on that, but if it didn’t work for some people well enough to imitate art, we wouldn’t have a problem.

 

[Reynard]

Is it impossible to tell in principle? or impossible to tell in practice? Because if it's the former I reject this premise.

Regardless, I would argue it does matter.

I meant by eye, fromthe perspective of the consumer.

Because if it does matter, a whole lot of other purchases we make on a regular basis start to get fuzzy, ethically speaking.

 

[Raiztt]

Sure, I agree on that, but if it didn’t work for some people well enough to imitate art, we wouldn’t have a problem.

You're always going to have value-less, principle-less people who are materialists at heart and only have the most superficial appreciation for anything - that's not a battle you're going to be able to win.

 

[Raiztt]

I meant by eye, fromthe perspective of the consumer.

Because if it does matter, a whole lot of other purchases we make on a regular basis start to get fuzzy, ethically speaking.

Absolutely.

 

[Oncewasbenji]

At the end of the day, if your solution to GM shortage is to replace them with AI, then I never want anything to do with your game. I love GMing and I cannot imagine how humilating it would feel to buy product of company that openly said they don't want me here.

So much support for this comment. They identified that dms buy most of the product and support things and then sort of planned to replace them in the hope they make everybody a player? Dunno how planning to replace the most invested part of a fan base or turn them into the people you found out don't spend money. If they ever move into ai dms, I'd finish up my dnd games and move my many groups to other games or keep playing the stuff I already have and not move forward. I already stopped buying stuff post ogl and moved to coc, but this would be the nail in the coffin.

 

[timbannock]

First of all, that's anecdotal evidence, that means nothing because no one of us has been there to witness it in its original context nor do we know the speciffic people. Second, it sounds to me like you did the majority of work and, quite frankly, we cannot tell if what AI provided wasn't actually dragging down the overall result, but you didn't see it out of lack of belief in yourself. Quite frankly, I think you're selling yourself short in favor of glorifying worthless toy.

First of all, I'm happy to share more info about our experience; we're on a discussion forum, after all. So if you have specific questions that would help you see whether this had any value or not rather than dismissing our experience out of hand, shoot. I still have the history of prompts available and their outputs, plus a session writeup, and could poll my players and come back with specific recollections of their experiences.

Secondly, I'm not interested in glorifying anything. I used a tool, and it provided value to the gaming experience we all had at the table: it directly improved the content I had ready for that specific scene, based on very little (but notably highly specific, including setting-specific) context, and it worked in a matter of seconds.

Lastly, I'm against AI replacing...well, a lot. Certainly writers, artists, and creatives of any kind. But using it as a tool? I'd be an idiot to be against that simply out of hand; I ran this as a test to see what it can do, and it performed to my liking. I'd much prefer AI to do my laundry and dishes, but if what it can do today is make my gaming session easier and better, I'm at least open to exploring that, while at the same time being vocal about ensuring AI doesn't ruin people's livelihoods. In case you wanted know where I stand.

 

[Ruin Explorer]

But then--you likely never see the worst art humans turn out either.

You absolutely do. This is where you're flatly wrong. It's not even arguable. When you're in an art class, you see the art other people are making. You can't honestly live life among others and not see the art they make. And human art is constructed by an entirely different process to AI generation - it's not comparable. You can take a bad piece and make it better, or you can you reject and change your ideas, whatever - AI cannot do anything of the sort, it can only re-roll its random combos the word salad of prompts. This strikes me as an objection coming either from someone who has never participated in making art, in their life (which seems unlikely, but not impossible), or a place of almost fantasy - another world, a different world, where the artistic process is hidden and unavailable.

I will be honest, when you see AI art boosters on Twitter you often do seem them acting the like the tools to create have been denied to them, hidden from them - but it's not true. It's never true. They're always well-off Westerners who went to decent colleges. They chose not to engage with the making of art. It was never denied to them.

So saying "AI art is only good when human curated" isn't really saying anything special to me.

That's on you. That you don't get it isn't on me.

It's particularly of note that the obviously low taste levels and weak aesthetic sense of a lot of AI art fans is part of what's holding AI art back, part of what is continuing to make it look distinctive and kind of crap - because the pieces being selected for are not usually the most artistically interesting, not the most similar to really skilled, striking or beautiful art, they're usually just the ones that nail the prompt and look "decent" - i.e. not obviously embarrassing (but they sometimes still are) - often as I've pointed out in this wildly overwrought, overdetailed way.

To be clear this is a subject I find quite interesting - I'm not averse at all to using AI art tools to explore what they can do, and I kind of hope one day to find one that's actually impressive, but the current limitations on their fundamental functionality, and the fact that they seem to be creating increasingly not decreasingly same-y images is unfortunate.

 

[Thomas Shey]

You absolutely do. This is where you're flatly wrong. It's not even arguable.

It is when I'm talking about the public. The public doesn't see what's done in an art class, either.

That's on you. That you don't get it isn't on me.

And it isn't my obligation that you see things the same as I do, either.

 

[SlyFlourish]

I know. I'm a broken record. But--

If there is a group of 5 players who can't find a GM, there is really a group of 4 players and a GM who needs to step up.

I did a poll on this a while ago and found that most DMs took the role because no one else would and there wouldn't be a game without it. So that supports your proposal.

 

[Ruin Explorer]

It is when I'm talking about the public. The public doesn't see what's done in an art class, either.

Yes they do. Because every school teaches art - or practically every one. We all know how art is created. We've all the seen the gamut created by the combination of talent, skill, practice, ideas and so on.

You seem to be under a bizarre misapprehension that an even slightly trained (including self-taught) artist will just randomly churn out terrible pieces that they secrete away in their studios or something. No. That's not a thing. Sure, trained artists make pieces that they're less happy with - usually they're left unfinished, but not always, sometimes they're finished and improved, sometimes they're reworked, in many cases they're just part of the artistic process - but even those pieces will not be "terrible" in any genuine sense - some of them have sold for staggering sums. They're not going randomly have the wrong kind of shading, or randomly draw something "bad" or pop out an extra arm or something. It's just not how it works. I'm mystified that you seem to trying to suggest that "the public" would be in some way put off by an artistic process most of them have some understanding of because they've done it.