Other D&D Variant Simple 1D6 D&D variant created with ChatGPT

[The Firebird]

Have you played the system? Several rules seem odd to me. For example, the rangers +1 damage vs a marked target is strictly worse than the fighters flat +1 to damage. Why would I play a ranger?

 

[kermit4karate]

And now you're just trolling!

I disagree. A difference of opinion isn't trolling.

I don't agree with your statement that an "AI/LLM can do certain things, other things it absolutely sucks at..." In terms of TTRPG development, I disagree with that. I believe that in a fair comparison with humans, meaning that if you allot a human 5 minutes to perform a specific creative task by themselves, and then you also give an LLM like ChatGPT 5 minutes of processing time to perform the same creative task, ChatGPT wins 99.999% of the time already. I think it's already on a minute-by-minute basis far more capable than humans are. And that's ignoring the fact that it and other AI/LLMs continue to grow more capable every day.

I don't agree with the common refrain that LLMs make mistakes, so therefore they're still inferior to humans. Humans make mistakes too. Lots of them. The difference that gets ignored far too often is that the LLM iterates over seconds. Its second draft takes another 10 seconds to produce. A human's could take weeks.

 

[kermit4karate]

Have you played the system? Several rules seem odd to me. For example, the rangers +1 damage vs a marked target is strictly worse than the fighters flat +1 to damage. Why would I play a ranger?

Yes, I've run it half a dozen times, and it was a blast. Very lightweight, obviously, and fast. Perfect for younger players or beginner adults.

Mind you, I'm not holding this up as a big deal or the end-all-be-all final iteration of the concept. This was just a few-minute thought exercise. That's how long I've put into it. I've been filling in a lot of the gameplay blanks myself as DM. I'll continue to tweak the two-pager here because I love the simplicity and the gameplay. This little document seems unassuming, but it's really the product of, frankly, billions of dollars of processing time and gigawatts of electricity on the AI side. That's the thing about AI. This looks like a nothingburger little game with a couple little flaws, but it was still produced after analyzing millions of facts and figures about TTRPG generated by actual humans.

 

[The Firebird]

Yes, I've run it half a dozen times, and it was a blast. Very lightweight, obviously, and fast. Perfect for younger players or beginner adults.

Mind you, I'm not holding this up as a big deal or the end-all-be-all final iteration of the concept. This was just a few-minute thought exercise. That's how long I've put into it. I've been filling in a lot of the gameplay blanks myself as DM. I'll continue to tweak the two-pager here because I love the simplicity and the gameplay. This little document seems unassuming, but it's really the product of, frankly, billions of dollars of processing time and gigawatts of electricity on the AI side. That's the thing about AI. This looks like a nothingburger little game with a couple little flaws, but it was still produced after analyzing millions of facts and figures about TTRPG generated by actual humans.

Playtesting is an iterative process; writing the rules and layout is a part of it. And there is a discursive component, where you run the game, see what worked and what didn't, and modify accordingly. I consider this part of the design time.

What sorts of adventures did you run in your playtest? Did the players find the classes well balanced? What kind of mods do you think the system is suited for--dungeon crawls, hexcrawls, 5e hardcovers?

 

[kermit4karate]

What sorts of adventures did you run in your playtest? Did the players find the classes well balanced? What kind of mods do you think the system is suited for--dungeon crawls, hexcrawls, 5e hardcovers?

Completely agree that playtesting is an iterative process.

My players for this have been pre-teens, teens and beginner adults. All have been too busy enjoying the game to care about the class balance, quite honestly. They simply haven't been concerned, but their enjoyment has proven to me that the mechanics are generally sound and contribute to fun -- the ultimate goal.

I've run similar groups through other game systems, many of the big names, and the challenges and question marks were far greater.

 

[The Firebird]

Completely agree that playtesting is an iterative process.

My players for this have been pre-teens, teens and beginner adults. All have been too busy enjoying the game to care about the class balance, quite honestly. They simply haven't been concerned, but their enjoyment has proven to me that the mechanics are generally sound and contribute to fun -- the ultimate goal.

I've run similar groups through other game systems, many of the big names, and the challenges and question marks were far greater.

Are you willing to share any details about those sessions--for example what mods you ran, if you had a fighter and a ranger or a wizard/sorcerer at the same table? Did anyone play a warlock, and if so what was their pact boon?

Some details from actual play would help demonstrate the system.

 

[kermit4karate]

Are you willing to share any details about those sessions--for example what mods you ran, if you had a fighter and a ranger or a wizard/sorcerer at the same table? Did anyone play a warlock, and if so what was their pact boon?

Some details from actual play would help demonstrate the system.

Not that complicated. Entirely roleplaying, no maps, miniatures, hex grid. Just simple, fast roleplaying. Here was a blurb written (by me, a human) after the scene introducing the first character, Osa, a 1st-level elven wizard, who's being played by a 9-year-old girl.

Again, no one is/was breaking down the system to find its weaknesses. That hasn't been the goal. The goal has only been to have fun and to maximize the time invested into it by everyone.

"Re: Osa, she works for Oober with her adoptive dad, Gromly, who runs the business. Gromly's a hill dwarf. Oober makes the best fried turkey in Fireforge. At Oober, crows fly out every shift to take orders from customers. Customers who see the crows just shout, "OOOOOBERRRR!" Then the crows fly back to the restaurant where Gromly and Osa fill the orders. Osa then delivers them by goat cart.

One day, Osa is delivering a 10-piece order of fried turkey to a powerful wizard in his tower when a giant gargoyle dragon suddenly breaks through the tower wall and kills the wizard after a brief battle. Osa witnesses the whole thing! The gargoyle then flies away, leaving Osa standing there in the ruins of the wizard's sanctuary.

She sees the deceased wizard's staff laying there on the floor and picks it up. It's the Staff of Sorcery!

Later, back at the restaurant, 2 bandits attempt to rob the place, but Osa stops them using the staff and her own magic. She casts Mage Hand and steals a pouch worn by one of the bandits. It was filled with coins! She uses the coins to buy potions"

Is it simplistic? Absolutely? Is it fun? Yes, I strongly believe so based on my experience with it. Is it meant to be something greater than it seems? No, it is not.

 

[The Firebird]

Not that complicated. Entirely roleplaying, no maps, miniatures, hex grid. Just simple, fast roleplaying. Here was a blurb written (by me, a human) after the scene introducing the first character, Osa, a 1st-level elven wizard, who's being played by a 9-year-old girl.

Again, no one is/was breaking down the system to find its weaknesses. That hasn't been the goal. The goal has only been to have fun and to maximize the time invested into it by everyone.

"Re: Osa, she works for Oober with her adoptive dad, Gromly, who runs the business. Gromly's a hill dwarf. Oober makes the best fried turkey in Fireforge. At Oober, crows fly out every shift to take orders from customers. Customers who see the crows just shout, "OOOOOBERRRR!" Then the crows fly back to the restaurant where Gromly and Osa fill the orders. Osa then delivers them by goat cart.

One day, Osa is delivering a 10-piece order of fried turkey to a powerful wizard in his tower when a giant gargoyle dragon suddenly breaks through the tower wall and kills the wizard after a brief battle. Osa witnesses the whole thing! The gargoyle then flies away, leaving Osa standing there in the ruins of the wizard's sanctuary.

She sees the deceased wizard's staff laying there on the floor and picks it up. It's the Staff of Sorcery!

Later, back at the restaurant, 2 bandits attempt to rob the place, but Osa stops them using the staff and her own magic. She casts Mage Hand and steals a pouch worn by one of the bandits. It was filled with coins! She uses the coins to buy potions"

Is it simplistic? Absolutely? Is it fun? Yes, I strongly believe so based on my experience with it. Is it meant to be something greater than it seems? No, it is not.

That's a fascinating scenario; written yourself? I don't see a lot of mechanics there though--is Mage Hand from the staff? It isn't included in the list of spells.

 

[kermit4karate]

That's a fascinating scenario; written yourself? I don't see a lot of mechanics there though--is Mage Hand from the staff? It isn't included in the list of spells.

Thank you. Yes, by me. This was just a writeup after a session to save it for posterity.

I think it's pretty apparent from the heading and stylistic items that the system is based on D&D, so yes, the full D&D spell list is available, and the ways to adjust the vast majority of those spells to fit the system is fairly obvious in most cases. I don't think it really accomplishes much to add those couple extra pages for all the spells. Just my opinion on that. I'm very familiar with D&D and rely on my familiarity here as the system is based upon it.

 

[Simon Miles]

Let me start by saying that the negative comments with little more argument then "But it's made by humans, thus better!" argument is going to drive more people into the arms of AI/LLM generated content.

AI/LLM are tools, tools used by humans. Those humans decide how to use the tools, and what rolls out depends on those humans. That does NOT mean that what rolls out is (any) good or well thought out. Something like this is probably more of a thought experiment then anything else, as many before you pointed out flaws in the system and things that were missing. This is more of a show of what an AI/LLM can throwup with little input, finessing and/or human editing.

I've been using Deepseek (r1 free) for generating room descriptions for the Undermountain adventure (5e Dungeon of the Mad Mage) from the little context that was given for each room. Just getting an acceptable output took a while to figure out, things from atmosphere, dungeon construction and general features for each level. And even then getting out exactly what I wanted wasn't happening, technical issues, memory issues, things I didn't like. Getting an AI/LLM to spit out exactly what you want in the style you want is like herding cats. You need to realize that good is good enough, and when it isn't, manual editing and/or rewriting entire sections is your friend! I've done the first five levels + Skullport, that's a few hundred descriptions. Could I have written those 100% myself? Absolutely, but how long would that have taken? Would it actually be better? Very long and probably not, unless I spent even more time on it. It still took a LOT of work. I then put it through an AI powered text-to-speech service, also a lot of work (and money to get a good quality output), but still less and better then if I did all the voice acting myself. My players really like this and didn't really notice (yet) that the text that's being read is AI generated.

Last week I started with Midjourney for image generation, getting that to function exactly to my wishes is even worse, it's like herding angry cats! Again, quite a bit of money, quite a bit of time. For the first session I settled on images that illustrated not exactly what was there, but gave an overall atmosphere. Sure, they figured out quickly that they were AI generated images, but they don't care, they like the atmosphere it creates. Midjourney gives you far more tools to edit and specify exactly what you want, but again you need knowledge and skills to make it work better for you, taking up even more time to learn new skills. But that's still less time then drawing/painting it yourself, even if you've been trained for that (like I have been), now imagine people that have not been trained for that. And again, will my human made illustrations be better then what the AI can generate? Probably not. And hiring someone else that does it in the exact style you want is going to be expensive, and will take WAY too much time to complete. My intention is to have atleast one illustration for every room/encounter, that's going to be hundreds of images.

AI/LLM is a tool for me to create more immersion/enjoyment for my players in a more realistic time/money budget. While leaving me time to create more bespoke adventure components for the adventure. In the same way that Waterdeep: Dungeon of the Mad Mage saved me oodles of time/money as a DM. I see no one complaining about published adventures being the ruin of smalltime bespoke illustrators/writers DMs... Not everyone likes published adventures, to be honest the quality/writing is actually lacking a bit with most of the WotC stuff anyway, the Deepseek writing is an actual improvement over that... And in the past I would have written my own adventures, have done many a time. But having a full time job that's brain intensive tends to mess that up, being older I also have more interests that distract me, as well as responsibilities. You don't have to use published adventures, you don't have to use AI/LLMs, you don't have to use D&D(5e).

That said, there are MANY, many RPGs I would use before ever considering using an RPG created by an AI/LLM. Even one page systems by writers I trust WAY more then ChatGPT. I would LOVE to spend $100-$200 to get a digital collection of 500 excellent illustrations made by human illustrators in style X about exactly subject Y, but not many others would, would they be able to sell a 1000+ of those bundles at that price? Probably not, because if they could, they would. In my case the artists that I want the style of are either dead or retired and at an advanced age (or have moved on from the style they did many decades ago). Also keep in mind that not everyone has a well paid job which results in a decent amount of disposable income, and in many different parts of the world, what's considered 'good' makes a magnitude of difference.

Wow! So, could you have written it yourself? Yes.
And you have explained yourself quite clearly, I understand the benefits that AI is giving you, so how does that play out for you? Get your questions so well-tailored that you need to intervene less and less? When does it stop being YOUR creation?
There is certainly a skill to getting AI to do what you want to do right, absolutely, and it is very useful for generating information, researching (although check what it comes up with) and developing ideas, certainly, but is that enjoyable? Do you find it rewarding on a Human level?
I write my own stuff, I draw my own stuff (it's not brilliant) and I love doing it - it's mine and I can be proud of it. I certainly don't make enough money out of it to pay for the effort I put in, but that's OK, I enjoy the process. Getting AI to do just seems such a wasted opportunity.
And if you're using AI because you can't afford the art, how will that play out? I The whole state of the creative process at the moment is being commoditised, there's less skills being learned and used, de-skilling the work force never ends well for the workforce.
If you feel you have to use AI to achieve what you want to achieve then I guess you'll go on doing it; you do you - but please make sure people know it's AI.