[HN Gopher] LLM based agents as Dungeon Masters
       ___________________________________________________________________
        
       LLM based agents as Dungeon Masters
        
       Author : utiiiD
       Score  : 112 points
       Date   : 2025-01-14 15:42 UTC (7 hours ago)
        
 (HTM) web link (studenttheses.uu.nl)
 (TXT) w3m dump (studenttheses.uu.nl)
        
       | Aeolun wrote:
       | Based on my experiences with this. Keeping context relevant is
       | the hardest part. Your human GM will remember that funny remark
       | from the session 3 years ago, but the LLM?
        
         | worthless-trash wrote:
         | I'd love to see some human & machine co-op for DM. That'd be
         | super helpful.
        
           | 2099miles wrote:
           | Now this is solid, like an ai enhanced Evernote, but for
           | organization, not generation/creation.
        
             | Sanzig wrote:
             | I've been meaning to take a crack at doing this - I'd like
             | to use Whisper to transcribe session recordings and then
             | have an LLM build out a campaign wiki. I enjoy being a DM
             | but note taking and organization is my least favourite
             | part.
        
           | cdiamand wrote:
           | I've used LLM's in this capacity, and it's awesome. It
           | quickly becomes a crutch.
        
         | ratedgene wrote:
         | I think we just haven't built complex enough architectures to
         | allow this. I have a few ideas boiling that would help
         | facilitate long term context understanding and recall.
        
         | cloudking wrote:
         | Maybe this is a solution https://www.letta.com/
        
           | potatoman22 wrote:
           | A context-based retrieval/memory system would be cool, too.
           | Pull in relevant events based on the group's location and
           | NPCs they're with.
        
         | mirages wrote:
         | Also for that same module, is it able to integrate it in a
         | broader campaign. I expanded the lore and why the players got
         | here with extra quests, fluff and mystery and they only reached
         | said dungeon at 2nd session only.
         | 
         | Also the way a PC died due to a rat bite that could only be
         | cured by magic (5e of this module is ironically harsher than
         | the 3.5) as he was losing max HP every 24H. As the players
         | expressed dislike with that character the owning player was
         | willing to go for a new character and I had planned a big drama
         | scene where the players exit in emergency the dungeon and try
         | to rally the nearet village where there's a priestessd and
         | happens that I could match the rolls so he would die in the
         | priestess hands.
         | 
         | But I made the mistake to allow them to spend the night to get
         | their 3rd level which would have allowed the druid to get his
         | cure illnesses spell botching the set up.
         | 
         | Happens that I decided to exploit the fact that all other
         | character the previous days made an offering to Beshaba to
         | curse that character and force rolls during night (and try to
         | find a way to make the new character come into play).
         | 
         | How it unfolded : - they were sleeping and it was the bard's
         | turn for watch
         | 
         | - the bard was a follower of Tharizdun and was about to
         | sacrifice the dieing character as said character was agonizing
         | 
         | - the new character was a Kara-turian enforcer that was chasing
         | a yokai (he didn't knew) that used other people as disguise,
         | made it happen that the yokai choose the dieing character "by
         | coincidence" appearance
         | 
         | - the yokai being chased opens a portal while hiding to the
         | dungeon
         | 
         | - the new character litteraly pops through a Wild Magic portal
         | that pushed away the bard and tries to bash the old character
         | as the old character runes on his skin glow a last time as he
         | dies and repels everybody
         | 
         | - made the new character pop naked as I wasn't paying attention
         | to what the player was saying when he was listing his inventory
         | 
         | - I let them handle the big mess
        
         | Kuinox wrote:
         | Neuro-sama, an AI VTuber streamer, manages to do this. There
         | are topics brought along multiple streams and manages to
         | remember details of previous streams.
        
           | jacoblambda wrote:
           | With soemthing like Neuro-sama I wouldn't doubt that Vedal is
           | doing a lot of liftwork behind the scenes to keep sufficient
           | context available to Neuro-sama's LLM.
        
         | lemoncookiechip wrote:
         | It's that: Spacial awareness, struggling to maintain the
         | personas (and often talking for the player/s), difficulty
         | improvising, pacing issues, lack of initiative, and just an
         | over reliance on prompting to keep going correctly.
        
       | 2099miles wrote:
       | This is so interesting that people want this. This is beyond the
       | guy saying "people don't like making music so we made ai so it's
       | easier and faster to just prompt it to make music" . Like in my
       | experience the best part of d&d is the dungeon master who knows
       | their friends making a story and details specifically for fun and
       | the fun of the group. And the interactions between players and
       | the dm is where I derived the most enjoyment, automating that
       | sounds insane and peak confusion/self defeating.
        
         | airstrike wrote:
         | Some people don't have friends they can play with :sadge:
        
           | foobarian wrote:
           | This. At home it's me and my one kid, and having an
           | additional party as a DM would be priceless.
        
         | Melomomololo wrote:
         | Just that finding a good DM is hard
        
         | dingnuts wrote:
         | they think they want it -- that doesn't mean they will actually
         | like it if they get it
        
         | prettyblocks wrote:
         | I think it's more about the challenge/curiosity of creating the
         | implementation. I'm not sure these AI driven text-RPGs will
         | find long term audiences.
        
           | pmichaud wrote:
           | They are a step on the road to fully responsive rpg worlds
           | though, which don't have to be text based.
        
             | JohnMakin wrote:
             | It's been written at length here and elsewhere by game
             | devs, but this isn't a thing that anyone would truly want.
             | A purely AI generated or controlled world would have no
             | constraints, and be fundamentally untestable - games aren't
             | really games unless they have constraints. Even the
             | 'purest' sandboxes have some kind of constraint buried
             | within them, and I think you'd find an RPG of this type
             | extremely boring, at least with current technology.
        
               | krisoft wrote:
               | > this isn't a thing that anyone would truly want.
               | 
               | Citation needed.
               | 
               | > A purely AI generated or controlled world would have no
               | constraints
               | 
               | That's a shitty AI then. Make a better one. I can play
               | 2000 Vampire: The Masquerade games with 2000 different
               | groups. They will each be different, but they will also
               | be each distinctly Vampire: The Masquerade ttrpg games.
               | If the AI you are thinking about can't do the same, then
               | think of a better AI.
               | 
               | > at least with current technology.
               | 
               | Well. Who is the group who will make the "next
               | technology"? Should we work on that, or just lay down on
               | the ground and wait for it to fall from the sky? Testing
               | what are the limits of the current technology (as done in
               | the paper we are talking about here) is the way to get
               | there. Or at least to systematically answer the question
               | of where and what are we lacking.
        
               | JohnMakin wrote:
               | > Citation needed.
               | 
               | Lol, a citation of what? This is my opinion statement and
               | the rest of my post follows it.
               | 
               | > That's a shitty AI then. Make a better one. I can play
               | 2000 Vampire: The Masquerade games with 2000 different
               | groups. They will each be different, but they will also
               | be each distinctly Vampire: The Masquerade ttrpg games.
               | If the AI you are thinking about can't do the same, then
               | think of a better AI.
               | 
               | Sure, I'll get right on that.
               | 
               | > Well. Who is the group who will make the "next
               | technology"? Should we work on that, or just lay down on
               | the ground and wait for it to fall from the sky? Testing
               | what are the limits of the current technology (as done in
               | the paper we are talking about here) is the way to get
               | there. Or at least to systematically answer the question
               | of where and what are we lacking.
               | 
               | I'm really unsure of what or who you are addressing here
               | but it certainly isn't anything I've written in my post.
        
               | krisoft wrote:
               | > citation of what?
               | 
               | Citation that nobody wants what you described? The
               | sentence which I was quoting.
               | 
               | > This is my opinion statement
               | 
               | Your opinon can be that "I don't want this." "nobody
               | wants this" is refers to things outside of your head. Do
               | you see the difference between the two?
               | 
               | > it certainly isn't anything I've written in my post.
               | 
               | Your post is suffused with defeatism. The 3 "no"s it
               | contains are: "nobody wants this", "with current
               | technology this cannot be fun" and an implicit "we can't
               | make the next technology". I believe each of those are
               | wrong, and I'm calling you out on the attitude.
        
               | JohnMakin wrote:
               | Ok, then what advances are being made in AI technology in
               | this gaming that lends you such confidence? Care to make
               | any citations yourself here? I don't really care what you
               | think of my attitude, nor does it make for productive
               | discussion or good posting.
        
               | krisoft wrote:
               | > Care to make any citations yourself here?
               | 
               | Happily. I know you are wrong on the "nobody wants this"
               | statement because I want it. With a sweeping generic
               | statement like "nobody wants this" a single example is
               | enough to disprove it. There you have it.
               | 
               | > what advances are being made in AI technology in this
               | gaming that lends you such confidence?
               | 
               | There is a ton of experimenting going on. AI Dungeon and
               | Deep Realms are the two obvious ones. I don't think
               | anyone has found the golden solution yet, but that is
               | also not evidence that no such thing exists.
        
               | int_19h wrote:
               | There's no reason why an AI-driven sandbox cannot have
               | constraints, as well.
               | 
               | Now it's true that, with the current crop of LLMs, a
               | persistent enough player would always be able to break
               | through them. But if it takes conscious and deliberate
               | effort, I think it's reasonable to say that whatever
               | experience the person gets as a result, they were asking
               | for it.
        
               | sentimentscan wrote:
               | I mean this isn't it fun to generate ancient rome/alice
               | in wonderland/medivial Poland kind of the world?
        
           | michaelcampbell wrote:
           | > I think it's more about the challenge/curiosity of creating
           | the implementation.
           | 
           | Totally this, at least for me, in some circumstances.
           | 
           | TOU's be damned, I've written bots for some online games I've
           | played, not because I want the XP or money or whatever that
           | the bot could do without me working for it, but rather
           | because I found writing the bots fun and engaging.
           | 
           | Before anyone gets in an uproar, I didn't sell them, nor any
           | of the in-game resources gained from them. I was watching
           | them basically all the time, because that's what I was there
           | for - to see my creation work. And I purposely didn't
           | interfere with other "real" players.
        
         | esafak wrote:
         | The modern thing to do would be to automate the game, watch the
         | bots play each other, and make a reaction video for TikTok.
        
           | michaelcampbell wrote:
           | Isn't this a modern take on the yarn that ended up with
           | students all just bringing a tape recorder to the lecture
           | hall after the lecturer just played a pre-recorded tape as
           | the lecture?
        
             | variaga wrote:
             | That was a scene from the movie "Real Genius"
        
         | ge96 wrote:
         | I was watching a video on YT, heard a cool song, tried to
         | soundhound it, turns out it was an AI generated song, I felt
         | like I was "owned" damn.
        
         | JohnMakin wrote:
         | > This is so interesting that people want this
         | 
         | I love being a DM but it is no mystery to me. Being a DM is a
         | _lot_ of work. And occasionally, a lot of annoyance. You not
         | only have to facilitate (and sometimes create from scratch) an
         | engaging story that keeps people coming back, you have to
         | wrangle busy schedules and personalities that is often
         | annoying. Lots of times you 'll have a bunch of people willing
         | to play, but no one willing to DM. So to me it's not surprising
         | at all, and I experimented with AI in running a game, and
         | quickly concluded it could never be good at it because it's so
         | insanely suggestible and has poor memory.
        
           | erosivesoul wrote:
           | That would be my takeaway too. There is room for AI DMs, but
           | they need to get a lot better before they're really fun to
           | play with. I tried a few AI RP just to see how it works and
           | it was pretty boring.
        
           | PaulHoule wrote:
           | Personally I can't stand to run a D&D game as players take it
           | all too seriously.
           | 
           | I will run _Toon_ , _Call of Cthulhu_ or _Paranoia_ any day,
           | the latter without a scenario as I can kill off their all
           | their clones in my very dangerous Alpha Complex and have them
           | rolling on the floor laughing the whole time with a help of a
           | stack of prerolled character sheets and some random encounter
           | tables. (I 'd expect an LLM to be able to do the same)
           | 
           | Contrast that to the famous _Bloodstone_ campaign which is
           | the pinnacle of D &D scenarios but can't really be
           | challenging to the players because players have to win over
           | and over again if you're going to use most of the material.
        
             | thom wrote:
             | I DM for early teens and I would kill for a D&D party that
             | took it all too seriously. :)
        
               | PaulHoule wrote:
               | Try a simpler game. I think a lot of people think TTRPG =
               | D&D and the world is worse off for it.
               | 
               | There are numerous tactics that work to face the "not
               | serious" problems you have in a game for "young adults".
               | 
               | For instance, serious players get resentful when somebody
               | not serious comes in late, forgets their character sheet,
               | etc. You could lose either or both of them, but with a
               | little prep you don't have to. In _Paranoia_ it 's easy
               | to shove a preroll into their hands, give them a 1-2
               | minute briefing from "The Computer" and build up tension
               | around this character who mysteriously appears (and if
               | the new player complains that they don't know the rules
               | tell them they're not allowed to know the rules!)
               | 
               |  _Toon_ is the epitome of  "not serious" and, like the
               | other two games I've mentioned, is a game where you can
               | buy one book and have everything you need, including your
               | first scenario.
        
               | thom wrote:
               | I think whatever rules we tried to play, the nob jokes
               | would persist.
        
               | BerislavLopac wrote:
               | Try Tales from the Loop --
               | https://freeleaguepublishing.com/games/tales-from-the-
               | loop-r...
        
           | scudsworth wrote:
           | i mean this is on point regarding the effort needed to run a
           | game, but also llms don't really solve any of the problems
           | you listed, so while people want _something_ it doesn't seem
           | like they're crying out for this. also, would love an example
           | of the suggestible ai DM if you have one handy lol
        
           | klik99 wrote:
           | I think the previous posters point was that an LLM DM is
           | boring due to it's generality and lacks the specific quirks
           | of having a human DM with their own viewpoint and
           | understanding of the players, which I agree with. I did some
           | experiments with earlier ChatGPT models for world building
           | and DMing and found it to be so boring, getting it to do
           | anything interesting or giving any kind of push back was so
           | hard. Since they are an averaging of all knowledge / previous
           | creativity you end up with a smooth surface, but part of what
           | makes stories interesting are the rough edges.
           | 
           | However I also agree with you that being a DM is a
           | prohibitive amount of work for someone, say, with kids and a
           | job. It would be awesome to have an LLM as an assistant,
           | maybe feeding in parts of the story and querying it for ideas
           | when you're in a bind. But having it run as a full DM, at
           | least right now, will likely lead to a boring experience.
        
             | thom wrote:
             | Yep, my experience using ChatGPT as a helper is very good.
             | It can very quickly cook up a custom monster, give it
             | relevant stats, and create some flavourful actions and
             | attacks to make it unique. Lately I've been trying to hook
             | this up to D&D Beyond, as it's just some fairly simple POST
             | payloads. If I can get to the point where I can describe a
             | vague encounter, and run it in the Beyond encounter tracker
             | with zero effort, that would be amazing, and a lifesaver
             | when the party goes off and does nutty stuff. Beyond that,
             | its story ideas are fairly generic but fine if you really
             | have no time, and it can do a decent job of the occasional
             | flowery monologue if you need it.
        
               | klik99 wrote:
               | If you make progress on the api part, would be awesome to
               | see a write up on HN about it, I'd be really interested
               | in how this develops!
        
           | loudmax wrote:
           | I tend to agree. I used to run Call of Cthulhu in high
           | school, and there was a lot of preparation involved in
           | running a good scenario. Some people are good at winging it
           | and making stuff up as they go along. I never was. The best
           | experiences for me and my players was always when I'd
           | meticulously designed my own scenario, or used a store-bought
           | scenario and read it thoroughly. Either way, hours of prep.
           | 
           | I would love to have an AI as an assistant Dungeon Master (or
           | game master, or Keeper, or what have you). That is, one
           | person in a group of players maintains the role of a master
           | storyteller, but the AI is ready to fill in details or
           | suggest ways to get the players back on track. This would
           | probably be tedious if you're interacting with the LLM
           | entirely through text, and having to manually keep it up to
           | date with the story. But it could work well if you have a
           | model that understands spoken language listening in on the
           | game and generating cool images and making private
           | suggestions to the game master.
        
         | derektank wrote:
         | DMing is, in my opinion, very time consuming. Prepping an
         | adventure, familiarizing yourself with the rules, trying to
         | incorporate character backstory in to the narrative, all takes
         | time. As someone that can only play D&D if I am DMing, because
         | none of my friends have the desire or inclination to do so, I
         | would be very happy to pay money for an LLM dungeon master that
         | lets me just play the game without all the prep time. I just
         | don't have 4 extra hours a week like I did in college.
        
         | empath75 wrote:
         | Try doing this while you're driving with the gpt4o advanced
         | audio mode. It's a nice way to kill 40 minutes or so without
         | having to look at a screen. Just tell it you want to play an
         | RPG with it, give it a setting, describe your character and go.
         | It'll mostly be more of a choose your own adventure than a real
         | RPG, but it can sometimes be quite entertaining.
        
         | utiiiD wrote:
         | Agreed on DM making the experience special. The cognitive load
         | on a DM is very high though. They have to digest information on
         | the game setting and the monsters, synthesize scenes and react
         | to players' interactions all the while staying true to the
         | narrative. I think LLM's can play a big part in assisting human
         | DMs by either providing low-fidelity ideas for "inspiraton",
         | commonsense based on their training on D&D texts and literature
         | or high fidelity text in some cases to be directly presented to
         | the players.
        
         | moralestapia wrote:
         | >This is so interesting that people want this.
         | 
         | Go outside. There's people for everything.
        
           | michaelcampbell wrote:
           | He said it was interesting, not baffling.
        
             | moralestapia wrote:
             | And I said what I said.
        
               | michaelcampbell wrote:
               | And all tautologies are tautological.
        
               | moralestapia wrote:
               | At least make an effort to understand what a tautology
               | is.
        
         | krisoft wrote:
         | > Like in my experience the best part of d&d is the dungeon
         | master who knows their friends making a story and details
         | specifically for fun and the fun of the group.
         | 
         | Sure.
         | 
         | There are two reason why I can think of someone making a
         | Dungeon Master LLm.
         | 
         | One is that when there is no cake we eat bread.
         | 
         | Don't get me wrong. I'm a DM, and I love playing d&d with my
         | friends. I totally agree with the sentiment you are sharing.
         | But people who are willing, and able to DM for others are not
         | evenly distributed. There is a lot more people who would like
         | to play TTRPGs than people who is willing to step into the DM
         | role.
         | 
         | So in that sense think of this as a substitutions for those
         | games which would not happen otherwise, because they don't have
         | a DM. Or the only person who would DM them is an ass. Or their
         | DM has burnt out.
         | 
         | Is some game better than no game? Sometimes. Depends on how
         | good that game is. And we won't know how good the substitute
         | can be without trying. Heck maybe more people will play, and
         | they will realise how easy is to DM actually.
         | 
         | The other reason is the sheer challenge of it. Dnd has a lot of
         | rules. There are the obvious ones you can read in the book. But
         | there are also un-written rules. Like object-permanence. If a
         | goblin steals a diamond ring from us, and we slay them within
         | minutes they damn well have the diamond ring on their bodies
         | somewhere. If three displacer beasts ambush us and we slay 2
         | there damn well be 1 more accounted for in some sense.
         | 
         | There are also "story-writing" rules. If we went through hell
         | and high-water to obtain an arrow of dragon slaying after the
         | blacksmith told us about the legend of it, he better not just
         | pull one out of his ass the next time we see him. If the whole
         | lore of goddess X is that they are kind and caring then they
         | should better be at least not cruel when we meet them. These
         | are all hard for an LLM. They are also easy for a human to
         | evaluate. Because we just feel when they are not right.
         | Therefore it is a good challenge to evaluate how good we are at
         | this "making a bucket of sand smart" task.
        
         | wintermutestwin wrote:
         | I am an "everything is custom tailored to my players" DM and I
         | use LLMs quite a lot as an assistant. Speeding up prep time is
         | always welcome. Using an LLM directly as a DM? Oh hell no.
         | 
         | Also, I ran a session over Zoom and their AI summary was so
         | useful!
        
         | mumbisChungo wrote:
         | Preparing a campaign is an awful lot of work, which at least in
         | my case is why my friend group almost never plays.
        
         | TeMPOraL wrote:
         | Two reasons:
         | 
         | 1) "LLM DM" isn't merely mean substituting for human DM in a
         | D&D session. The same capability can be used as a component in
         | a video game, to breathe life into the game world, have it
         | interactively react and evolve along with the player.
         | 
         | EDIT: Take a game like Rimworld, that relies on a scripted RNG
         | dubbed a "storyteller", to decide what random events to hit you
         | with and how hard. It's fun early on, but if you're into role-
         | playing, you'll quickly realize there's no evolving story
         | behind it, just stateless RNG. An LLM DM is exactly what could
         | add that story, make overcoming challenges feel meaningful and
         | allow for player decisions to actually impact the world deeply.
         | 
         | 2) There are people like me, who would love to participate in
         | an RPG session, but for various reasons never got invited to
         | those when at school, and now, due to demands of parenthood,
         | can't exactly make time to coordinate with the few people
         | around who are still playing.
         | 
         | There are more, but those are the two that are apparent to me.
        
           | giantrobot wrote:
           | > An LLM DM is exactly what could add that story, make
           | overcoming challenges feel meaningful and allow for player
           | decisions to actually impact the world deeply.
           | 
           | No it's not. I don't think you're going to find an LLM with a
           | large enough context window to have a meaningfully involving
           | story spanning multiple sessions.
           | 
           | An LLM isn't going to craft a story element tailored to a
           | character, or more importantly, an individual _player_. It 's
           | not going to understand Sam couldn't make last week's
           | session. An LLM also doesn't really understand the game rules
           | and isn't going to be able to adjudicate house rules based on
           | fun factor.
           | 
           | LLMs can be great tools for gaming but I think their value as
           | a game master is limited. They'll be no better a game master
           | than a MadLibs book.
        
             | mlyle wrote:
             | His example:
             | 
             | Rimworld is a great universe where we think about
             | characters' stories, and there's really just like, a couple
             | dozen attributes and straightforward ways they interact
             | with the game.
             | 
             | An LLM context window could easily have 20 times as much
             | interpersonal state, and make it interact in much more
             | unexpected (but plausible) ways. That's going to be a
             | surprising and rewarding gaming experience once someone
             | figures it out.
        
               | TeMPOraL wrote:
               | Context window is arbitrary and can be adjusted on
               | demand. When a new random event needs to be generated,
               | and then fleshed out, the context can contain e.g. list
               | of facts about the story so far, the overall story arc,
               | summary of main characters or plot threads. This can be
               | used by LLM to decide e.g. which faction will attack, and
               | who will be on it, and what their goal will be, etc.
               | After the event concludes, it just becomes another line
               | in story event history. Meanwhile, that can be fed to a
               | differently prompted LLM to evolve the plot arc, update
               | motivations of background characters, etc.
               | 
               | I have a feeling people imagine LLMs as end-to-end DMs
               | that should somehow remember everything and do everything
               | in one inference round. That's not what they are. They're
               | building blocks. They're to be chained and mixed with
               | classical flow control, algorithms, and data storage (as
               | well as the whole interactive game mechanics, in
               | videogame context).
        
               | mlyle wrote:
               | Maybe. But for something like Rimworld++++, you don't
               | need all that sophistication. You need a pile of relevant
               | facts and a clear task to determine something about the
               | game or write some text for the user. Sure, curating and
               | retrieving selectively would probably be even better and
               | more flexible.
        
             | TeMPOraL wrote:
             | > _I don 't think you're going to find an LLM with a large
             | enough context window to have a meaningfully involving
             | story spanning multiple sessions._
             | 
             | Sure you will.
             | 
             | > _An LLM isn 't going to craft a story element tailored to
             | a character, or more importantly, an individual player._
             | 
             | Sure it is.
             | 
             | > _An LLM also doesn 't really understand the game rules
             | and isn't going to be able to adjudicate house rules based
             | on fun factor._
             | 
             | Sure it will.
             | 
             | You need to use the tools for their purpose, not for the
             | opposite of it. LLMs have finite context, you need to
             | manage it. LLMs don't have a built-in loop, you need to
             | supply it.
             | 
             | Character stats, names, details about players - those are
             | inputs, and structured ones at that. LLMs shouldn't store
             | them - that's what storage media are for, whether in-memory
             | or a database or a piece of paper. Nor should they
             | manipulate them directly - that's what game systems are
             | for, whether implemented in code or in a rulebook run on a
             | human DM. LLMs are to make decisions - local, intuitive
             | decisions, based on what is in their context. That could be
             | deciding what a character says in a given situation. Or how
             | to continue the story based on worldbuilding database. Or
             | how to update the worldbuilding database based on what it
             | just added to the story. Etc.
        
               | sentimentscan wrote:
               | I have solved it in my two games by using two systems in
               | my future game: 1. LLM "text" info ,about world, player,
               | text descriptions of world/decisions and so one. 2.
               | Typical D&D stuff with rolls, names, details, decisions
               | that are simple logic.
        
             | gwern wrote:
             | > I don't think you're going to find an LLM with a large
             | enough context window to have a meaningfully involving
             | story spanning multiple sessions.
             | 
             | First, you don't need much of any context window because
             | you can finetune the LLM. Don't mistake specific
             | engineering choices and tradeoffs and deployment
             | convenience for intrinsic limitations of the technology.
             | 
             | Second, LLMs like Gemini now have context windows of
             | millions of tokens, corresponding to millions of words.
             | Seems like enough for 'multiple sessions'.
             | 
             | > An LLM isn't going to craft a story element tailored to a
             | character, or more importantly, an individual player. It's
             | not going to understand Sam couldn't make last week's
             | session. An LLM also doesn't really understand the game
             | rules and isn't going to be able to adjudicate house rules
             | based on fun factor.
             | 
             | An LLM can do all of that, and you definitely do not know
             | that they can't.
             | 
             | > They'll be no better a game master than a MadLibs book.
             | 
             | They've been better than a Madlibs book since AI Dungeon 1
             | which was like 6 years ago.
        
               | someone3876 wrote:
               | Have you actually used Gemini? I use it a lot for
               | translation, and its context window is more like 150k
               | tokens, rather than the 2M context window they say it
               | has.
        
               | Der_Einzige wrote:
               | Be that as it may, long context window models which are
               | good are not a mirage. By say late 2027, when the LLM
               | providers figure out that they're using the wrong
               | samplers, they will figure out how to get you 2 million
               | output tokens per LLM call which stay coherent.
        
             | sentimentscan wrote:
             | >I don't think you're going to find an LLM with a large
             | enough context window to have a meaningfully involving
             | story spanning multiple sessions
             | 
             | You don't need to provide every single previous information
             | to llm, use LLM to summarise previous ones and it gets
             | really compact. It works quite well.
        
         | fonix232 wrote:
         | I can totally see the appeal of using LLMs to _help_ the DM.
         | Not to replace it.
         | 
         | I DM a few games of The Expanse, and using LLMs to plan ahead
         | was a godsend. No, I didn't utilise it to write the story for
         | me - instead I used it to test my planned story and see which
         | way my players might strafe off the road, so I can plan for
         | those. Basically simulated a game using an LLM that acted in
         | place of multiple characters, allowed those to run free (within
         | certain limits, obviously you can't have the LLM players do a
         | dozen actions without the DM having a say), and essentially
         | mapped the potential "off branches", story pathways I didn't
         | plan for initially. This has allowed me to be prepared for the
         | usual dumbass things players might do, such as heading for a
         | strip club in the middle of a total disaster where they
         | (figuratively) have dozens of arrows pointing to the goal of
         | the chapter.
         | 
         | Another interesting aspect of using AI for TTRPGs is to create
         | atmospherics. For Expanse based games, I've bought a number of
         | tile packs and such, to appreciate the artists who put work
         | into it, but I simply don't have the funds to commission a few
         | dozen acrylic matte style scenery images (which I usually put
         | up on my projector, combined with some Hue lights to create the
         | visual atmosphere). With AI, I can even generate them on the
         | fly, should my little gremlins stray off the path. Same for
         | music - AI can incredibly easily generate an atmospheric
         | soundtrack that fits the current scenery, with just a few
         | words, while I can still pay attention to the players.
         | 
         | But fully replacing the DM? That's silly.
        
         | calibas wrote:
         | Consider video game RPGs. They're largely based upon D&D, yet
         | they remove the dungeon master entirely. They are enormously
         | more popular than D&D itself.
         | 
         | Now imagine something in between, where you have a video game,
         | but the NPCs and parts of the story are controlled by an LLM.
         | You can give the players much more freedom, and the creators
         | don't have to write thousands of lines of dialog to account for
         | every possible choice a player can make. The game doesn't have
         | to be "on rails" so much, the LLM can help speed the story
         | along when the player gets confused, and you can have NPCs with
         | much more depth than just several lines of static dialog.
         | 
         | How well this will work in practice remains to be seen. In my
         | experience, ChatGPT itself is a painfully generic DM that
         | relies upon repetitive fantasy tropes. You still need an actual
         | human being to create an interesting story and add depth to the
         | world.
        
         | tjakab wrote:
         | I largely see it as the digital next step up from something
         | like the Mythic Game Master Emulator, which is popular for solo
         | play and things like trying out new systems.
         | 
         | And there's quite a lot of us that like to play but because of
         | life commitments, getting together with a group on a regular
         | schedule is difficult.
        
         | johnfn wrote:
         | This is nothing new. Bringing ideas from DND into video games
         | is as old as video games themselves. In interviews, John
         | Carmack talks often about how he used to play DND with his
         | friends and then try to take that experience into the games he
         | made. And it goes back even further than that - Rogue, the
         | primogenitor of all roguelike games, was inspired by DND as
         | well. I could find a bunch more examples, but you get the idea.
        
       | noodletheworld wrote:
       | Alas, I was desperately keen to read transcripts of actual
       | gameplay and all we got was user surveys?
       | 
       | Was there a structured combat system as sort of this or was it a
       | talking only kind of thing? Who knows?
       | 
       | Trying to get empirical evidence that an LLM can even remotely
       | plausibly work as a DM with no social aspect and (as far as I can
       | tell, reading the paper) no programmed system of stats, rolls,
       | combat etc. seems impressive.
       | 
       | ...but was it that? Or just a DnD themed chatGPT conversation? Or
       | a text adventure with an LLM describing each "room"?
       | 
       | Did the LLM actually have _agency_ to make decisions and perform
       | tasks, or was it not an agent at all, just a conversation?
       | 
       | Without a transcript, all you can really say for _sure_ is yeah,
       | I agree; more research is needed.
        
       | empath75 wrote:
       | The main problem with doing this on chatgpt is that it is
       | _relentlessly_ cheerful and it's almost impossible for it to
       | produce any kind of interpersonal drama or threat or danger.
       | 
       | I tried to get it to run space opera about a diplomatic mission
       | to a newly recontacted planet, full of Game of Thrones-style
       | intrigue and plotting and scheming, and it was like playing with
       | a cheerily optimistic new UN intern that completely believes in
       | the power of compromise and diplomacy to solve all problems.
       | 
       | It was always like: "And so the two of you hashed out your
       | differences over a glass of Dubranian Forblik, and peace reigned
       | forever and ever after."
       | 
       | That's true of how it does role playing games and any kind of
       | fiction at all -- it always wants to tie a neat bow on it at the
       | end of every few paragraphs with a moral and everything.
       | 
       | You also have to ask it to use python to dice roll for anything
       | you want to potentially fail on, or it will always make
       | everything you do succeed wonderfully.
       | 
       | I will say this -- the advanced audio mode for D&D is amazing and
       | it really does act out the characters and it will occasionally
       | slip into different voices or even add sound effects, even though
       | it's not "allowed" to. It will also sometimes copy your voice and
       | act out what it thinks you should do instead of letting you talk,
       | though.
        
         | erehweb wrote:
         | Reminiscent of the Twilight Zone episode where a criminal ends
         | up in the afterlife. Spoilers in link
         | https://en.wikipedia.org/wiki/A_Nice_Place_to_Visit
        
           | empath75 wrote:
           | The old gpt2 engine that used to drive AI Dungeon had the
           | opposite problem, it was obviously trained on a ton of really
           | bad fan fiction and would frequently either shift into filthy
           | erotica or some kind of hyper violent serial killer story, no
           | matter how innocently the story started.
        
         | jgalt212 wrote:
         | The researchers encountered this.
         | 
         | > raised by 3 out of 7 players was the perceived lack of danger
         | for their characters. Participants noted that the gameplay did
         | not present sufficient threats or challenges, which diminished
         | the sense of urgency and excitement typically associated with
         | D&D adventures.
        
         | int_19h wrote:
         | Indeed. But for stuff like this, ChatGPT is overkill. It's
         | better to get a dedicated RP finetune of LLaMA, Qwen, or some
         | other open weights model (you can still run it in the cloud if
         | you don't have hardware to do so locally). There are enough
         | finetunes around by now that you can "dial in" how dark you
         | want it, but for some examples:
         | 
         | https://huggingface.co/jukofyork/Dark-Miqu-70B
         | 
         | https://huggingface.co/SicariusSicariiStuff/Negative_LLAMA_7...
        
         | sentimentscan wrote:
         | Yep, in my game it tried always to "save" player it was
         | impossible for LLM to jail or kill a player to end a game. I
         | had to explicitly end it by game logic, not by LLM.
        
       | cmpalmer52 wrote:
       | Yeah, completely automatic DMing just makes it like an open-ended
       | computer game. On the other hand, the AI generated NPC responses
       | are better than I could have come up with quickly, which makes me
       | think co-DMing with an AI partner might be fun, particularly if
       | they get better at remembering the details. That would let the
       | human DM control the flow of the story without worrying that Thug
       | #4 has taken 3hp of damage and is Dazzled. Of course, I most
       | often use Foundry or Roll20 these days and they do a lot of that
       | for you.
       | 
       | I wonder how well it could do for game summaries and recaps?
        
       | short_sells_poo wrote:
       | I find this idea fascinating, and I think a lot of very
       | interesting emergent behavior can be added to video games by
       | having something like an LLM act as a Dungeon Master. Rather than
       | having to pre-program a bunch of choices that the player is
       | allowed to pick between, have an AI model evolve the story and
       | just move the pieces on the story board based on what the player
       | actually does. Story driven games these days are still very much
       | railroaded. They are like interactive movies. The player has very
       | limited agency. They can't really pick any choice which the
       | designers haven't thought to implement upfront.
       | 
       | At the same time, I'm personally not super enthusiastic about
       | using LLMs for a pen and paper game. Let's assume for a moment
       | that we have free will, then the most fun aspect of PnP dungeon
       | mastering is the fact that the DM has agency. It adds an (IMO)
       | very fun mini-game where the players try to get away with as much
       | shenanigans as they can, and the DMs job is to try to thwart
       | these shenanigans in the most entertaining ways possible. The
       | keyword is on "try" - the GM has to put entertaining obstacles in
       | front of the players to keep the game fun, but ultimately the
       | players should have an avenue of success. Even if they don't
       | always succeed, they need to succeed enough and when they fail
       | they need to feel that it was fair.
       | 
       | I feel that with an AI DM, this goes out the window. At least
       | with the current crop of AI, I would never feel that I'm facing
       | an agent with it's own free will, rather just a machine. As such,
       | it cannot replace a human DM for the PnP purposes.
        
       | cdiamand wrote:
       | Last year, I built a DM for myself using the OpenAI api and an
       | elevenLabs voice generator. I asked it set my character in
       | Baldur's Gate, so it could pull upon the huge amount of DnD
       | source material it had been trained on.
       | 
       | A few takeaways:
       | 
       | 1. An LLM based DM can give the player essentially infinite
       | richness and description on anything they ask for.
       | 
       | 2. There is difficulty in setting the rules for the LLM to follow
       | that match the DnD rulebook. But this is possible to solve for.
       | Also, I found the LLM to be too pliable as a DM. I kept getting
       | my way, or getting my hand held through scenarios. Maybe this is
       | a feature?
       | 
       | 3. My conversation quickly began to approach the context window
       | for the LLM and some RAG engineering is very necessary to keep
       | the LLM informed about the key parts of your history.
       | 
       | 4. Most importantly, I found that I most enjoy the human
       | connection that I get through DnD and an LLM with a voice doesn't
       | really satisfy that.
        
         | coder543 wrote:
         | > My conversation quickly began to approach the context window
         | for the LLM and some RAG engineering is very necessary to keep
         | the LLM informed about the key parts of your history
         | 
         | Assuming we're talking about GPT-4o, that 128k context window
         | theoretically corresponds to somewhere around 73,000 words.
         | People talk at around 100 words per minute in conversation, so
         | that would be about 730 minutes of context, or about 12 hours.
         | The Gemini models can do up to 2 million tokens of context...
         | which we could extrapolate to 11,400 minutes of context (190
         | hours), which _might_ be enough?
         | 
         | I would say GPT-4o was only good up to about 64k tokens the
         | last time I really tested large context stuff, so let's call
         | that 6 hours of context. In my experience, Gemini's massive
         | context windows are actually able to retain a lot of
         | information... it's not like there's only 64k usable or
         | something. Google has some kind of secret sauce there.
         | 
         | One could imagine architecting the app to use Gemini's Context
         | Caching[0] to keep response times low, since it wouldn't need
         | to re-process the entire session for every response. The
         | application would just spin up a new context cache in the
         | background every 10 minutes or so and delete the old one,
         | reducing the amount of recent conversation that would have to
         | be re-processed each time to generate a response.
         | 
         | I've just never seen RAG work particularly well... and fitting
         | everything into the context is very nice by comparison.
         | 
         | But, one alternative to RAG would be a form of context
         | compression... you could give the LLM several tools/functions
         | for managing the context. The LLM would be instructed to use
         | these tools to record (and update) the names and information of
         | different characters, places, and items that the players
         | encounter, important events that have occurred during the game,
         | as well as information about who the current players are and
         | what items and abilities those players have, and then the LLM
         | would be provided with this "memory" in the context in place of
         | a complete conversational record. The LLM would then just
         | receive (for example) the most recent 15 or 30 minutes of
         | conversation, in addition to that memory.
         | 
         | > I found the LLM to be too pliable as a DM.
         | 
         | I haven't tried using an LLM as a DM, but in my experience,
         | GPT-4o is happy to hold its ground on things. This isn't like
         | the GPT-3.5 days where it was a total pushover for anything and
         | everything. I believe the big Gemini models are also stronger
         | than the old models used to be in this regard. Maybe you just
         | need a stricter prompt for the LLM that tells it how to behave?
         | 
         | I also think the new trend of "reasoning" models could be very
         | interesting for use cases like this. The model could try to
         | (privately) develop a more cohesive picture of the situation
         | before responding to new developments. You could already do
         | this to some extent by making multiple calls to the LLM, one
         | for the LLM to "think", and then another for the LLM to provide
         | a response that would actually go to the players.
         | 
         | One could also imagine giving the LLM access to other functions
         | that it could call, such as the ability to play music and sound
         | effects from a pre-defined library of sounds, or to roll the
         | dice using an external random number generator.
         | 
         | > 4. Most importantly, I found that I most enjoy the human
         | connection that I get through DnD and an LLM with a voice
         | doesn't really satisfy that.
         | 
         | Sure, maybe it's not something people actually want... who
         | knows. But, I think it looks pretty fun.[1]
         | 
         | One of the harder things with this would be helping the LLM
         | learn when to speak and when to just let the players talk
         | amongst themselves. A simple solution could just be to have a
         | button that the players can press when they want, which will
         | then trigger the LLM to respond to what's been recently said,
         | but it would be cool to just have a natural flow.
         | 
         | [0]: https://ai.google.dev/gemini-api/docs/caching
         | 
         | [1]: https://www.youtube.com/watch?v=9oBdLUEayGI
        
         | pbronez wrote:
         | I did something similar, but tried to get several agents to
         | play a DnD round together. It basically worked, but was
         | insipid.
        
         | int_19h wrote:
         | > Also, I found the LLM to be too pliable as a DM. I kept
         | getting my way, or getting my hand held through scenarios.
         | Maybe this is a feature?
         | 
         | LLMs are fine-tuned to be "helpful assistants", so they're
         | basically sycophantic.
        
       | Deukhoofd wrote:
       | Using a fine-tuned GPT-3.5 model is definitely a choice, why not
       | pick one of the newer models? The methodology only states they
       | use "ChatGPT" as LLM, but doesn't clarify the model until way
       | later, nor why they picked that model over other existing models.
       | 
       | The methodology also barely explains how they did their baseline
       | experiments with human DMs. Did they do them face-to-face, or via
       | text? Did they have different DMs in the 3 games they used as
       | baseline, or was it the same person? As it stands the research is
       | barely reproducible.
        
       | noufalibrahim wrote:
       | This is fascinating.
       | 
       | I don't have any experience with D&D but wanted to learn it to
       | play it with my kids. I used claude to learn the basic rules and
       | then had it help me create the scenario. Then I played as the dm
       | while it simulated being the players and then vice versa.
       | 
       | Really nice experience
        
       | bnetd wrote:
       | So speaking of sex dolls...
        
       | wuliwong wrote:
       | A while ago I was playing with chatgpt and had it create me a
       | text based game. It took some coaxing but eventually it actually
       | created a pretty compelling beginning to a game at least. This
       | wasn't D&D, I had chatgpt just make the rules but the interesting
       | part was creating a compelling story. Maybe it would have fallen
       | apart after a little bit of game play but it was neat. I could
       | see the fun of having completely unique and instantly created
       | modules to run through.
        
       | bsenftner wrote:
       | I've made several DMs for a variety of entertainments. It's as
       | much fun to create them as it is to play a scenario with them.
       | I've experimented with a few methods, such as providing them with
       | an ASCII map that looks like a hack/rogue map, giving them a
       | famous book as the scenario, giving them multiple books and or
       | famous fictional characters and then just letting them loose in a
       | DM/AI guided narrative the user is making decisions.
       | 
       | Of course, I have a "classic" DM that happens to be visiting here
       | on vacation from the dungeons & dragon's multiverse, where his
       | real job is being a DM for visiting tourists. There's a "Shaggy"
       | and his talking dog one can take LSD with when going to Woodstock
       | in '68. There's a StarTrek strategic tactical simulations
       | instructor. I quite like a Underground railroad "conductor" that
       | guides escaped slaves to freedom before the US Civil War.
       | 
       | I think these DM / interactive narrative applications have a huge
       | future in education and training.
        
       | SubiculumCode wrote:
       | I try to variance of this where I was the DM and the llm played
       | the player characters. It went okay but it was also a bit lame.
        
         | drak0n1c wrote:
         | An ideal entry role for LLM in tabletop may be NPC
         | companions/followers in the party that players/DM don't care
         | for roleplaying or find tedious. Set it to listen in on
         | conversations or VTT chat, and interject dialog on a rate-
         | limited basis. Could lead to unusual situational ideas or at
         | least humorous moments.
        
       | kelseyfrog wrote:
       | Last year, during a period of recovery, I hosted a ChatGPT game
       | with my nieces and newphew. I played the role of being a bride
       | between them and the LLM. I read aloud the text, and translated
       | their actions into queries.
       | 
       | With slight nudges, GPT performed well. It excelled at NPC
       | dialog, location description, and to some extent improvisation.
       | However, eventually the campaign fell apart on session four or
       | five. There was a disagreement between the players over exactly
       | how many maps we had acquired. As you know, answering this
       | question is a needle in a haystack problem and asking the LLM
       | proved to illicit conflicting responses. It ultimately led to me
       | concluding that pausing the campaign was the right choice and
       | accepting that we all still had an amazing time up to that point.
       | 
       | Which leads me back to the questions in the paper: > We believe
       | that with the above evaluation methods we can try to answer the
       | following questions: * How consistent is a LLM Agent in its
       | generative dialogue? * How well can a LLM Agent keep a user
       | engaged in a narrative plot? * How creative is a LLM Agent when
       | generating complex story driven narratives?
       | 
       | None of these are exactly relevant to my personal experience
       | running a TTRPG game using ChatGPT and what makes it succeed or
       | fail. What would make such a system an improvement is being able
       | to store and retrieve facts about players (HP, stats, inventory),
       | NPCs(names, location, history), and Places(items, descriptions,
       | inhabitants) in order to solve the needs-haystack problem.
       | Creating a world ontology and being able to CRUD facts against
       | such an ontology would be a game changer(literally).
       | 
       | Despite the ultimate demise of the game, the experiment was a
       | success. I'd highly encourage anyone with a laptop, a handful of
       | dice, and a group of interested friends to give a shot. It's fun,
       | memorable, and a unique way to pass the time and bond.
        
         | TeMPOraL wrote:
         | > _What would make such a system an improvement is being able
         | to store and retrieve facts about players (HP, stats,
         | inventory), NPCs(names, location, history), and Places(items,
         | descriptions, inhabitants) in order to solve the needs-haystack
         | problem. Creating a world ontology and being able to CRUD facts
         | against such an ontology would be a game changer(literally)._
         | 
         | Curiously, those are the exact things LLMs can't do well, and
         | are not really supposed to. This is all stuff you (or an
         | external system) should keep track of and supply to LLM in
         | context "just in time". This is to say, LLMs are an important
         | component, but alone they won't work. They need their tools :).
         | 
         | In short, LLMs are pure "system 1", the complete solution still
         | needs "system 2", which fortunately is more amenable to
         | classical computing approaches.
        
       | jrpt wrote:
       | I made something like this to let people explore the lore of my
       | game. It has an AI act like a dungeon master as you play through
       | a story. You can try it for free at:
       | https://orbsccg.com/adventures
       | 
       | The main game is a strategic collectible card game, but the
       | "adventure mode" is just for fun AI-powered stories.
        
       | karaterobot wrote:
       | This is a student thesis, which doesn't mean it's bad, but is
       | worth keeping in mind. I see that their control group size was
       | three people (in three different sessions), but I don't see how
       | many people they ran through the AI part of the experiment.
       | 
       | I was wondering the other day whether there were good services
       | for running tabletop games over AI. I don't know about good,
       | because I haven't tried them, but there are certainly a few
       | products like this today. Given that ChatGPT plus some fine-
       | tuning was comparable to a human GM in this experiment, I'd be
       | interested in another experiment that looked at whether these
       | products (which charge more money) offer any benefit over just
       | using ChatGPT. For them to be better than ChatGPT, it seems like
       | they'd almost have to be better than a human GM to be worth the
       | money.
        
       | devmor wrote:
       | Like others, I don't really understand why anyone would desire
       | this.
       | 
       | D&D is a social activity, why would I want to remove the most
       | core human component of a social activity. It'd be like someone
       | who enjoys going to a sports bar with friends deciding they'd
       | rather sit next to a vending machine.
        
         | bongodongobob wrote:
         | Do you take issue with Baldur's Gate 3? Video games in general?
         | Why not?
        
           | devmor wrote:
           | Baldur's Gate 3 (and other games of its nature) are narrative
           | experiences crafted by writers to convey a story. I don't
           | play BG3 when I want to play D&D, and when I do want to play
           | something like BG3 I certainly wouldn't be interested in a
           | machine generated amalgamation of other people's ideas with
           | no thought or emotion behind it - that would be fundamentally
           | pointless and a waste of my time - like reading Lorem Ipsum
           | instead of a novel.
        
       | lowsong wrote:
       | I am baffled as to why anyone would want this, or anything like
       | it.
       | 
       | Sure, it's a cool technical demo. But... the point of D&D is a
       | social game played with others. Even if you play a D&D-like video
       | game such as Baldur's Gate 3 (which I'd argue is a fundamentally
       | different experience to playing a tabletop RPG anyway), you're
       | experiencing a world and a story that someone else has crafted.
       | 
       | What's the point of replacing that social interaction, or that
       | connection to another person's creative vision through their art,
       | with an LLM? What value can it ever provide?
        
         | mog_dev wrote:
         | I imagine for people like me who do not have anyone nearby
         | willing to play D&D
        
           | samwiseg wrote:
           | Right, but why not play BG3? You know that an LLM is not
           | going to provide any meaningful narrative, or craft a thought
           | provoking story.
        
           | lowsong wrote:
           | I've been in a weekly D&D game for over a decade. I don't
           | keep playing it because of the _game_ of D &D (certainly not,
           | I could rant for a long time about the game's myriad
           | shortcomings across many editions). I play it because of the
           | friends I play it with, because of the social connection that
           | exists in and around the game.
           | 
           | To play a tabletop RPG without that isn't the same thing, and
           | to play with LLM is bankrupt of meaning. You'd be better off
           | picking up one of those old-school choose your own adventure
           | books or a video game like BG3. At least those were written
           | by someone with intent, at least there's meaning in the story
           | and setting. Or, finding an online group.
        
             | enasterosophes wrote:
             | Would it be fair to say that you also don't appreciate solo
             | rpgs?
        
             | mywittyname wrote:
             | People play games for a variety of reasons. While you enjoy
             | the social aspect, others may find that to be the worst
             | aspect of the game (or just don't have a social circle).
             | 
             | I grew up playing D&D alone in my room using LEGO. It was
             | great and I still have some of the sets I built as dungeons
             | and monsters that I built from reference pictures in the
             | Monster Manual.
             | 
             | Video games are different from solo role playing. It's like
             | trying to substitute shooting hoops in the driveway with
             | NBA '24.
        
         | Kiro wrote:
         | I would love a fully generated D&D campaign where I just input
         | some parameters, like a writing prompt, and get a tailored LLM
         | Dungeon Master organizing it. Whether it's the result of
         | someone's creative vision or not is irrelevant to me.
        
         | enasterosophes wrote:
         | I've found chatgpt useful for trying out D&D settings that I
         | don't normally get to experience in my usual group. It loses
         | the plot after a while, but it's enough for me to figure out
         | whether I dig the setting enough that I would want to pitch it
         | for a real game.
        
         | soneca wrote:
         | I am not interested in this, but an AI DM that allow human
         | players to play would keep the social aspect. Since being DM is
         | a higher threshold of knowledge and time investment, this could
         | unblock a social gathering, rather than substituting it.
         | 
         | Also, if it doesn't try to keep the story to strict guardrails,
         | the creativity and story creation would come essentially from
         | the human players.
         | 
         | I don't think those arguments are enough to make _me_ want to
         | use it, but I see the point and possible interesting use.
        
       | drak0n1c wrote:
       | For those averse to LLM defeating the social aspect of tabletop
       | roleplaying, perhaps a better entry role for an LLM agent is as
       | NPC party companions/followers. Set up the agent with a detailed
       | character sheet and hidden backstory/motivations and set it to
       | listen in on conversations or VTT chat, and interject dialog on a
       | non-spammy basis. Could lead to unusual situational ideas or at
       | least humorous moments.
        
         | bongodongobob wrote:
         | This is what our DM does. It works really well for NPCs and
         | saves him a shit ton of time and effort.
        
       | HanClinto wrote:
       | This is extremely interesting to me. I understand why so many
       | people are surprised that people would want this, but for
       | whatever reason, I'm very much in the target audience.
       | 
       | I'm a "perpetual DM" in most of my roleplaying groups, having led
       | campaigns spanning years, but very rarely do I get to participate
       | as a player. My kids love me running adventures and one-shots,
       | and while I enjoy it, people don't always recognize how much work
       | it is -- both the prep, as well as the mental effort of being
       | "on" for the entire duration of the adventure. I like afternoon
       | one-shot adventures, but I dislike reading through long
       | sourcebooks. I enjoy crafting puzzles and presenting challenges
       | to the players, but also recognize the mental effort that this
       | takes, and sometimes I just want a copilot to handle the lore and
       | the setting. I already rely on the rules-nerds in my group to act
       | as copilots for the specifics of game mechanics -- I don't have
       | time to read through that many tables and commit them to memory.
       | 
       | Re: datasets, the paper authors used a dataset that they created
       | by scraping Critical Role transcripts -- I doubt they had
       | permission for that. I like contributing to open datasets for
       | training open-source LLMs, and I think it would be really sweet
       | for a playgroup to be able to contribute their play transcripts
       | for such a thing. I would love to see a standard open-source
       | dataset be collected for this, and perhaps even a standardized
       | benchmark for quantifying the performance of particular LLMs in
       | RPG contexts -- rules compliance, needle-in-haystack fact
       | finding, consistency of roleplaying, understanding user intent,
       | challenge creation / resolution, etc.
        
       | c6o wrote:
       | My experience with D&D and LLM is that is a cheat sheet and a
       | great helper, specially for newbies like me, I'm a Dad of 4 that
       | plays DnD to teach some lessons and to get my kids out of the
       | screens
        
       | alasdairking wrote:
       | A good use for this is people wanting to try an RPG, but not
       | having a bunch of people to do that with. A parent wanting to try
       | out this D&D thing so he or she can run it with the kids, for
       | example.
        
       | gunalx wrote:
       | I found it to be a pretty OK first draft character creator, scene
       | described and occasional lore/world builder. Not really anything
       | more. Kinda a DM assistant more than a DM.
        
       | sentimentscan wrote:
       | I've created two AI LLM D&D-style games. The second one will soon
       | be released as a D&D-style game with Visual Novel elements (AI-
       | generated images_. Here's how I can address some common concerns
       | from comments above:                   Lack of Human and Social
       | Interactions: This is a significant drawback when you look it as
       | the social thing, however, they require scheduling. For me I
       | wanted to venture beyond the typical fantasy/sci-fi settings and
       | good bored of those D&D/warhammer world.              LLM
       | Versatility: LLMs can take you on wild (now non-NSFW) adventures.
       | I wanted to play a D&D-style game set in the Venetian Renaissance
       | and GPT delivered with accurate locations, families, and artists.
       | It can do the same with medieval settings from my country,
       | ancient Rome, surrealist landscapes, and whatever your favorite
       | books, movies, or games involve.              Customization: Want
       | a game master who replies in poetry, slang, in style of you
       | favourite author? No problem.              Context: This is a
       | tough one, but there are two approaches:             Retrieval-
       | Augmented Generation (RAG)             Summarization, and then
       | summarization of the summary. I've used this approach in my
       | previous startup and in this game.              Characters: I
       | utilised the randomness of different character styles. You might
       | meet smart/beautiful/evil/good characters with predefined styles,
       | and the LLM quite effectively supports roleplay.
       | 
       | Cons:                   Lack of Continuity: The biggest downside
       | is the lack of continuity. Even if I generate a world and
       | scenario, after a few rooms, it doesn't come together like a game
       | would, where previous events feed into current ones, even when I
       | provide again LLM with previous details. I kinda lack big picture
       | design of story. I am working on that
       | 
       | I'm currently running a private beta and looking for co-founders
       | (game/design/coding) in the EU, preferably Poland. Please email
       | me at contact@sentimentscanner.com for more information for beta
       | membership and so one.
        
       ___________________________________________________________________
       (page generated 2025-01-14 23:01 UTC)