RPG Evolution: The AI DM in Action

How might WOTC launch an AI-powered DM assistant?

How might WOTC launch an AI-powered DM assistant?

technology-4256272_1280.jpg

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!
 

log in or register to remove this ad

Michael Tresca

Michael Tresca


Reynard

Legend
More on topic: I think that AI tools to assist the GM will be a big deal and most VTTs and realm/campaign managers will incorporate them sooner rather than later (probably pending some resolution of open copyright questions).

I am pretty sure you could run D&D via Claude.ai v3 as it is, if you fed the parameters of an adventure into it. And for some people -- casual players whos main purpose is to hang out together, rather than any actual deep role-playing -- that will be sufficient. But we are probably a ways off from an AI GM that can actually produce novel, coherent output. Hell, sometimes I have trouble being simultaneously novel and coherent as a GM.
 

Horwath

Legend
This could mostly be used by DMs to make encounter design easier.

I.E: Hey AI, create 10 deadly+ encounters for X PC's of level Y based on various goblinoids and half dragon bosses. Every encounter needs to have minimum of 10 opponents and maximum of 20.

have 4 encounters more focus on martial NPCs, 3 on magic NPCs, and 3 on experts using lot's of alchemical items and traps.
 

Retros_x

Explorer
I see great potential for DM assistants and for random tables and other generators - tons of DM already use generative AI right now to get creative juices flowing.

What I don't really see are AI NPCs or even the full DM as AI. At least for me, it would rob the hobby of its novelty and would feel more like a video game or just a really weird artificial thing between video games and TTRPGs.
 

Celebrim

Legend
AI right now are limited to about 1500 words of context and can generally remember no more than about five things. There ability to reason from what they know is also pretty limited. As such, we are a long ways from having AI that can act as a GM. They'll do pretty good for the first two to four exchanges and then completely lose their train of thought (as it were, I'm not asserting that they can actually think yet).

But AI as a tool of empowering people and amplifying their own ability to produce content is something that is if not already here is not far away.
 


Right now it definitely seems like a context and memory issue. I tried several of the current AI models and as others have said, it starts off promising. If you create a cohesive prompt for a world you want to play in, then ask for several encounters with increasing difficulty the results have generally been passable. Occasionally you get an intro adventure dragon fight recommendation and when you point it out the responses have been "oh of course you're right, you wouldnt fight a dragon at level 1". Then the farther you get into things like mimicking a battle with initiative and rounds it tends to fragment and the AI loses awareness of details you've already gone over or rules you've told it to remember. I think we will get a lot farther once we can do things like create a character sheet and have it held in memory, but also be updateable. Same thing for rules systems. If we could say "I want to play using 5e rules, in a low-magic world, with lots of political intrigue, walk me through creating 4 pc's and start us off in a tavern..." and actually have it work, that would be amazing.
 


Give me a AI that listens in and tracks things my players forget like encumbrance and the gold they spent. Then let it chime in when needed with quips like "Actualy Morcath can't make the attack. He only bought 20 bolts for his hand crossbow" or "Not so fast Jandar the Red can only move half is speed picking up that spell book moved him up an encumbrance level"

Just an annoying sidekick that rules lawyers the heck out of them.
 

Remove ads

Remove ads

Top