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!

 

[Thomas Shey]

But the real solution to the lack of GMs is a) for more players to spend time behind the screen, and b) for existing GMs to not make it sound like its hard and no fun. GMing isn't that hard and it is a blast.

I'd have to suggest that the latter is an overgeneralization. It absolutely can be both relatively easy and fun, if you know yourself and your group well, but those ifs are not trivial in some cases. I stopped running for one group a few months ago (as I referenced in your thread) because it had become so unpleasant, and it doesn't take an enormous number of similar experiences for a GM to develop a rather conflicted view toward doing so.

 

[Oofta]

It is an ad hominem and fallacious point of discussion. It implicitly relies on base assumptions that all ethical quandaries should be handled similarly, and that if one is not entirely consistent all the time, their points should be disregarded.



Yes, and the one thing they did NOT establish in the show is the idea that, since you can't address every ethical question, you can just give in and address none of them. We still owe to each other a solid attempt to be good people, even if we cannot be perfect.

Which kind of blows your point about being hypocritical out of the water - perfection will be denied all of us, so cherry picking individual issues where they fail doesn't really indicate that they are wrong on this issue. The ethical choices for generative AI should be made without extraneous references to other issues.

In other words, the issue of rare earths is an off-topic distraction, deflection, or misdirection. Stick to the actual issue under discussion.

I was responding to a poster that states that using AI is no different than supporting child labor. Perhaps hypocrisy is the wrong term and I'm approaching the argument in the wrong way. But I stand by the fact that they are making hyperbolic associations and comparing two things that are not at all the same.

 

[Reynard]

I'd have to suggest that the latter is an overgeneralization. It absolutely can be both relatively easy and fun, if you know yourself and your group well, but those ifs are not trivial in some cases. I stopped running for one group a few months ago (as I referenced in your thread) because it had become so unpleasant, and it doesn't take an enormous number of similar experiences for a GM to develop a rather conflicted view toward doing so.

Sure, but my point is that if we want more GMs in the hobby, and fewer paid GMs, then we (existing GMs) need to bolster those new potential GMs' confidence. Way too many GMs go on and on about how hard it is (often, I think, as a weird kind of flex) and that has a negative impact on those potential GMs.

We did it when we were 10. They can do it too.

 

[Sorcerers Apprentice]

I think the best way to get more people into DM'ing is to make sure that being a DM is as fun as possible. Make it clear that the DM is a participant in the game as much as the players, and not just putting on a performance for them.

 

[Dire Bare]

Within the academic study of ethics, these two words you're using are synonyms. Unethical just means evil and vice versa. "Not very bad" is still a subsection of bad. I am not arguing about HOW bad it is, just that it IS bad.

I'll take your word for it. But . . . this is not a conversation among academics who study ethics.

 

[Reynard]

I think the best way to get more people into DM'ing is to make sure that being a DM is as fun as possible. Make it clear that the DM is a participant in the game as much as the players, and not just putting on a performance for them.

Right. The GM isn't the players' dancing monkey and more than the players are the GM's subjects. The paid GM thing can exacerbate this problem, I think.

 

[Thomas Shey]

Sure, but my point is that if we want more GMs in the hobby, and fewer paid GMs, then we (existing GMs) need to bolster those new potential GMs' confidence. Way too many GMs go on and on about how hard it is (often, I think, as a weird kind of flex) and that has a negative impact on those potential GMs.

We did it when we were 10. They can do it too.

The "hard" part is easy to argue against, especially with certain systems. Its the "work" part that is, perhaps, less self-evident.

 

[Clint_L]

Within the academic study of ethics, these two words you're using are synonyms. Unethical just means evil and vice versa. "Not very bad" is still a subsection of bad. I am not arguing about HOW bad it is, just that it IS bad.

[checks philosophy degree]

Nope, these words are not synonyms. Evil is a much broader term that relies to a significant degree on context. For example, if we are discussing natural evils like, say, an earthquake, we would not also call them unethical.

In general, if you want to denote that something is unethical, you just use that word: "unethical." Precision is important in philosophy, and "evil" tends to be a loaded term.

 

[NK96]

How might WOTC launch an AI-powered DM assistant?

View attachment 353521
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!

How about AI Game Master? It's my small, self-funded team's dream project—an AI dungeon master app that brings fresh dynamics to your tabletop! Check it out here: AI Game Master

 

[Mr Ali K]

How might WOTC launch an AI-powered DM assistant?

View attachment 353521
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!

Good Article, This is really interesting and something close to my heart, as a long-term gamer who has become involved in a project to develop a AI-powered Games Masters Assistant called www.LoreKeeper.com.

It seems most tools on the market are looking at the virtual TTRPG market. And for me, a fully automated AI GM is not something I would want to play with - it becomes more of a Computer game and the social interaction of TRPG's is one of the main reasons I play.

As other people have said, the main problem with GPT etc is that it forgets, and it's replies become out of context.
What we're developing is a tool to help GM's save and upload their campaign lore and then create storylines, npcs, encounters etc, all based on their relevant Lore.

If anyone wants to know more just shout.