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

Huh?

I would guess that most folks on this site don't plan on using AI to replace the DM. The technology isn't there yet anyway.

But . . . chill. "This website" isn't jumping in on a new fad, this article is @talien reporting on developments in our hobby. Love it or hate it, AI has been a part of the landscape for decades already, and continues to become a part of our lives as the technology improves and companies look for ways to increase their bottom lines.

We are discussing AI and how it might be used in D&D . . . for good or for ill.
In case of this fad all uses are for ill and that won't change until techbros won't move on to new get rich quick scheme or go bankrupt. Reporting on it only serves to add water to their propaganda mill and keep pushing their lie about how "AI is the future", when the crap they're selling isn't even real AI.
 

log in or register to remove this ad

timbannock

Hero
Supporter
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.
Or there is a group of 5 GMs just in search of the right game for each of them to run.

Or, less positive-for-the-TTRPG-side, 5 players looking for the right app-driven co-op board game. I'm not well-versed in that space, but I played several sessions of Journeys in Middle-Earth and once we got the hang of the system, we started adding roleplaying elements to it. And this was a group of mostly board gamers who had little experience and limited interest in TTRPGs.
 

Dire Bare

Legend
In case of this fad all uses are for ill and that won't change until techbros won't move on to new get rich quick scheme or go bankrupt. Reporting on it only serves to add water to their propaganda mill and keep pushing their lie about how "AI is the future", when the crap they're selling isn't even real AI.
Okay.
 

talien

Community Supporter
In case of this fad all uses are for ill and that won't change until techbros won't move on to new get rich quick scheme or go bankrupt. Reporting on it only serves to add water to their propaganda mill and keep pushing their lie about how "AI is the future", when the crap they're selling isn't even real AI.
Although AI has a lot in common with the crypto-fad, the barrier to entry for it is way lower. As others have pointed out, AI is something you can use right now (I certainly do) for running our own campaigns. That's a far cry from "replace all humans with AI." But you absolutely have the right to not participate; conversely, this series of article started with Hasbro/WOTC expressing interest in using AI. So we're discussing the possibilities of what that might look like, and I think that's healthy, if only so we can hash out what level of AI we're all willing to tolerate.

I try to use the term LLM, or Generative AI, to make it clear we're essentially talking to parrots (parrots who can cold-read like the best of "psychics"), not thinking machines, but point taken on how we position the technology.
 

Dire Bare

Legend
If WotC wants more people running the game, they need to design a game more people enjoy running. This does not mean make one less fun to play, but an actual reason that makes people want to run it.
This isn't a problem for just D&D 5E. This isn't even a problem for just D&D versus other RPGs. This is a problem for most RPGs as the entire category has been asymmetric since 1974.

Some RPGs do make the job of GM easier than others, but the basic problem applies to most, if not all, role-playing games.
 

Nebulous

Legend
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.
I don't see how current AI can replace a human DM. We aren't there yet technologically. The AI can't account for random things the player says or does, especially the more "outside the box" ideas someone might come up with, or a long string of rambling roleplaying it would react to. As an assistant DM to handle number crunching or other tertiary jobs, that sounds appealing.
 

timbannock

Hero
Supporter
This has been AI for nearly 30 years. Video games have given "mobs", the equivalent of D&D "monster", any entity not played by a character, an AI for path parsing, attack choosing/threat assessment, attack method, etc. Some they just want to turn tabletop into a video game?


Again, video games. WotC struggles with having GMs because nobody wants to. They made a version or versions of the game that too many people want to "play", but nobody wants to run. If the "most popular" edition is so good, then why does nobody want to run it? There is a reason the Banker is not a regular player option for Monopoly, and everyone shares the role. WotC is trying for this, and it does not quite fit with D&D.

If WotC wants more people running the game, they need to design a game more people enjoy running. This does not mean make one less fun to play, but an actual reason that makes people want to run it.

Reading many social media and watching videos, the backlash for running the game and doing ANYTHING that might offend someone to end up ridiculed online, or reviewed in sone "gamer horror stories" makes fewer people want to run the game. The strange modern gaming culture WotC hangs around with makes it too risky for many people to want to try for fear of being ostracized for making the simplest of mistakes socially, not even mechanics or rulings mistakes!

An automat DM is not going to fair better than a video game because it will offer, ONETRUEWAY, the way it was programmed and learned. Might be good for convention tournament where the players are competing like the years of old. Today a DM needs fkexibility and adaptability to the individual group of players he is running for above all else. AI can not do that, at keast not these locked LLMs that can not be tailored to smaller groups as they dont have memory to select which "rulings" to apply to the rules for one individual group versus another.

The short version, an AI DM is what is known as a fool's errand.
There's a lot here that I agree with, especially specific to WOTC. If they go into "AI as DM" to any degree, they really need to take a hard look at what DMing means, and it's very clear to me that they have not done so throughout 5E's lifecycle, though I'll reserve final judgment until I see what's in the 2024 DMG. But they've relied so hard on the community building up DMs rather than putting in the work themselves, and then they've relied on DDB being the primary tool for DMs, which it is both pretty comprehensive at but also woefully deficient in certain areas of usability for that role (house rules, creating custom monsters, items, etc.). I haven't seen them make great headway on that front, and their adventures continue to be extremely painful to use at the table.

In a lot of ways the solutions are about "generative" or procedural content, and there was a solution for that as early as OD&D: the clear procedures of dungeon exploration, wilderness travel, and combat turns, all the tables purpose-built to generate content for those procedures, and finally the codified processes for campaign building (hex maps, dungeon maps, and, later settlement maps). But as the game has expanded, and as 5E specifically tries to be the "edition of stuffing it with all the things," that sort of content is incredibly hard to handle in a usable way. AI could definitely help with that, and make procedural generation much, much faster, and allow for the processes to be automated, so a DM could easily run a game without devoting all that time and headspace to processes and procedures. But I don't really foresee WOTC understanding that to any great degree in the first place, so the implementation will likely be just more of DDB: piles and piles of information that's easier to sift through than it is from printed books, but still needs to be sifted through and stitched together by the hardworking hands of the DM.
 

Oofta

Legend
This has been AI for nearly 30 years. Video games have given "mobs", the equivalent of D&D "monster", any entity not played by a character, an AI for path parsing, attack choosing/threat assessment, attack method, etc. Some they just want to turn tabletop into a video game?


Again, video games. WotC struggles with having GMs because nobody wants to. They made a version or versions of the game that too many people want to "play", but nobody wants to run. If the "most popular" edition is so good, then why does nobody want to run it? There is a reason the Banker is not a regular player option for Monopoly, and everyone shares the role. WotC is trying for this, and it does not quite fit with D&D.

If WotC wants more people running the game, they need to design a game more people enjoy running. This does not mean make one less fun to play, but an actual reason that makes people want to run it.

Reading many social media and watching videos, the backlash for running the game and doing ANYTHING that might offend someone to end up ridiculed online, or reviewed in sone "gamer horror stories" makes fewer people want to run the game. The strange modern gaming culture WotC hangs around with makes it too risky for many people to want to try for fear of being ostracized for making the simplest of mistakes socially, not even mechanics or rulings mistakes!

An automat DM is not going to fair better than a video game because it will offer, ONETRUEWAY, the way it was programmed and learned. Might be good for convention tournament where the players are competing like the years of old. Today a DM needs fkexibility and adaptability to the individual group of players he is running for above all else. AI can not do that, at keast not these locked LLMs that can not be tailored to smaller groups as they dont have memory to select which "rulings" to apply to the rules for one individual group versus another.

The short version, an AI DM is what is known as a fool's errand.

The biggest challenge and holdback to people DMing has more to do with creativity and the ability to react to people's choices along with role playing multiple NPCs in game in my experience. The specific rules don't really change that unless you change the nature of the game. But then things based on, for example PbtA games just make everyone responsible to a degree for creatively adding to the story and lore (I'm sure I'm oversimplifying a bit) which doesn't really fix much of anything. It just puts the onus on everyone at the table.

Which is why I think a DM assistant could really boost people's confidence and capabilities. It's not that the assistant would run the game, but it could provide input and inspiration when asked. The DM, of course, would still make the final call. That, and I sometimes think the DM shortage is overblown. Is every DM above average? Of course not, doesn't mean it can't still be a fun game.
 

LesserThan

Explorer
This isn't a problem for just D&D 5E. This isn't even a problem for just D&D versus other RPGs. This is a problem for most RPGs
I do not disagree. I would not want to run a TRPG. Too much nonsense to track, but I would not wish to play one with too little to track as a player. Some build spreadsheet databases to track the smallest things for the games the run. They must be accountants.

But, some people, I would wager most, now and then, just have more interest in playing than running. Assymetrical I think you called it.
 

UngainlyTitan

Legend
Supporter
Sometimes you gotta jump in.the water.

Are you serious?

There are thousands of videos online to help folks get over that first hump. Surely 1 in 5 is capable?

I agree, WotC could be doing more to cultivate new GMs.
it is not about capability it is the willingness to screw it up. There has always been a shortage of DMs but in my opinion the unwillings to DM is related to the modern unwillingness to perform in public or dance sober.
 

Remove ads

Remove ads

Top