D&D General Can ChatGPT create a Campaign setting?


log in or register to remove this ad

Jer

Legend
Supporter
RE: Anything original

I mean, it is just remixing what it's given in a fairly sophisticated way, right? Is that what we do (King Lear vs. Oedipus at Colonus)? Is there anything new under the sun?
One major difference between what ChatGPT is doing and what we do (and there are so, so many) is that ChatGPT can literally only mix together what it has "read" to produce new text.

Humans, on the other hand, have a complex system of inputs that include not just what we've read but also what we've experienced. And our emotional responses to these things. Yes if you want to get essentialist these are chemical reactions to the experiences that lead to different brain states, but we have them and they are an input that Large Language Models - which only have language - do not.

What an LLM does is nothing like the way a human brain works and what it produces is going to be far, far more limited because its inputs are far more limited. This isn't even about whether or not it's possible to get a machine to reproduce what a human being does in a "strong AI" sense - LLMs are nowhere near the boundary for strong AI. They just remix text in a way that our brain says "good enough". Especially for things where we don't expect novelty but in fact want a standardized response (like the back-and-forth of a chat, or a form letter, or a 5 paragraph essay).
 



RE: Anything original

I mean, it is just remixing what it's given in a fairly sophisticated way, right? Is that what we do (King Lear vs. Oedipus at Colonus)? Is there anything new under the sun?

Discussing ChatGPT can understandably (maybe unavoidably) veer into existential "what does it all mean, man?" questions, so I get it. And I write and edit for a living—often about AI—so I'm clearly biased. But imo there's a difference between how AI does something like style transfer (applying a given set of features from one piece of content to another) without intent, cognition, or emotional expression, and how a person draws parallels and makes associations and chooses to configure language and meaning.

But at the end of the day, to me, it comes down to a question of scarcity: Is ChatGPT producing something of value that's currently in short supply or otherwise hard to obtain? The world is full of books and texts of all kinds, so I think no. And even if the model happens to produce something you think is neat, it's not like when you come across a well-written bit of text from an RPG designer, and can then dig into other work by them, or keep track of their future projects. ChatGPT basically wrote you a little accidental mandala, and there's no reason to think its output will be of specific interest again tomorrow, especially after whatever local interaction you had has been overwritten and blown away.
 

Clint_L

Hero
As writing, though, that is absolutely, as the kids say, mid. Just hackneyed "joke" after joke. As with every long-ish ChatGPT output I read, I wish I could get back the time I spent reading it, because they never produce anything interesting or original.
I can't answer for your subjective taste. But I can tell you that, objectively, that second memo is better than the vast majority of human beings would write given the same prompts. I find it delightful.

ChatGPT can, right now, write at a level sophisticated enough to easily pass most writing assignments through an undergraduate level. When given random samples, extremely experienced assessors cannot tell the difference between it, given smart prompts, and a human being, so I think we are fooling ourselves if we think that we would do better.

I am going to suggest that many folks are looking at this technology the wrong way. It is not a replacement for human beings, but it is an incredibly potent new tool. Just as other forms of AI have revolutionized fields ranging from mathematics to animation, it is going to revolution writing, including creative writing.
 

Cadence

Legend
Supporter
Discussing ChatGPT can understandably (maybe unavoidably) veer into existential "what does it all mean, man?" questions, so I get it. And I write and edit for a living—often about AI—so I'm clearly biased. But imo there's a difference between how AI does something like style transfer (applying a given set of features from one piece of content to another) without intent, cognition, or emotional expression, and how a person draws parallels and makes associations and chooses to configure language and meaning.

But at the end of the day, to me, it comes down to a question of scarcity: Is ChatGPT producing something of value that's currently in short supply or otherwise hard to obtain? The world is full of books and texts of all kinds, so I think no. And even if the model happens to produce something you think is neat, it's not like when you come across a well-written bit of text from an RPG designer, and can then dig into other work by them, or keep track of their future projects. ChatGPT basically wrote you a little accidental mandala, and there's no reason to think its output will be of specific interest again tomorrow, especially after whatever local interaction you had has been overwritten and blown away.

The part I worry about a bit is all of the stuff that people do that doesn't seem great. And not just the person (student, employee, whatnot) half-arseing something because they don't care or are time pressured. But I think about "one hit wonders". I would not be surprised if the brilliant poems, songs, and stories are safe - so that the various anthology and best of's by humans will still stand out. But how many collections and albums by professionals have a few real standouts and then a bunch of meh? How hard will it be to get it to make the common parts that don't work but are part of paying the bills?
 

Clint_L

Hero
Or like I tell my students - we've been "less than 10 years away" from self-driving cars for around 13 years at this point.
I have students using ChatGPT with their work right now. Every school and university does. This is not happening tomorrow or next year. It's happened. The revolution has occurred. What comes next is evolution.
 

Cadence

Legend
Supporter
I am going to suggest that many folks are looking at this technology the wrong way. It is not a replacement for human beings, but it is an incredibly potent new tool. Just as other forms of AI have revolutionized fields ranging from mathematics to animation, it is going to revolution writing, including creative writing.

In Chess, AI hasn't really replaced people because people enjoy it for the competition and the people-part of it. And I like a lot of the ways an AI can back up a doctor, for example.

But in general I wish I was as optimistic as you about it not just turning into a replacement everywhere it can for things that involve money and profits.

People used to value buy local and supporting neighborhood stores. And now we have Amazon, Walmart, and a lot less of the rest. Right now a lot of people are angry about AI art. Right now.
 

Jer

Legend
Supporter
I have students using ChatGPT with their work right now. Every school and university does. This is not happening tomorrow or next year. It's happened. The revolution has occurred. What comes next is evolution.
This is because your students are being asked to put together relatively trivial writing assignments that are there to build their skills not because you're asking them to do wonderfully creative work.

It's the same in my field - programming. Yes some of these models can put together work that 1st or 2nd year students can do. That's because we ask them to write things to learn how to write not because we actually care about that output. Frankly every essay you might ask your students to write for a class probably exists on the internet somewhere already given the density of the text out there.

Ask ChatGPT to put together a novel for you. It's terrible. Ask ChatGPT to develop an actual solution to a real world programming problem. It can't. It's nuts for us at the professional educator level because it short-circuits our learning processes - it makes it hard to tell if the students are actually practicing or just turning in what an AI has written. But that's because what our students generally churn out is banal stuff that is the same year after year with subtle variations as practice to scaffold them up to doing more interesting things. The exact kind of form-filling that ChatGPT is good at.
 

Burt Baccara

Explorer

Burt Baccara

Explorer
This likely has to do with the resources being allocated to it.
For sure, another cause may be the finetuning to get Chat-GPT to be more reliable and not make stuff up as much. At first, it was great at saying false claims with convincing conviction—it still does, but less often.

Remembering what was said upstream is an advertised feature on new chat screen. I am sure this is just a hiccup, but it's been like that for about a week now and really impacts how one interacts with Chat-GTP and in some ways its usefulness.
 

Clint_L

Hero
A lot of folks are not responding my argument, so I must not be explaining it well. Maybe I should enlist ChatGPT.

Will ChatGPT write the next Great American Novel on its own? No, not as it currently exists. Could it be enlisted to write the next Great American Novel? Quite possibly.

Here's an analogy: most people would agree that Andy Warhol is a highly important artist of the 20th century, despite the fact that much of what came out of Andy Warhol's Factory and was attributed to him was physically done by other artists working under his direction (many other visual artists have worked similarly, from Michelangelo to Banksy). Similarly, we consider Martin Scorsese a great film direction, despite the fact that most of the production of any of "his" films was done by someone else. That is because we recognize the creative vision guiding the process, and we see the other contributions as secondary.

Similarly, ChatGPT gives every human being a personal assistant that is a highly competent and incredibly fast writer. Stable Diffusion and similar technologies are giving us highly competent artists. We still have to provide the imagination and guidance. But how much more can we create, on our own, using these technologies?

Let's go back to the original question. Imagine that I want to create a detailed setting for my campaign, based around, I dunno, penguins. I'm a good writer, and I am capable, but do I really want to invest the time producing a 200 page guide to Pengunia? Maybe, but probably not. But a lot of that writing would effectively be drudge work. With ChatGPT, I am suddenly Martin Scorsese. I can get it produce a ton of iterations on different ideas. I can throw in my own writing whenever I want. I can tweak and massage and experiment. Artistically, I can let ideas build up far faster than I could writing on my own. And I can probably write a pretty cool guide, original to the world and specifically tailored to MY needs, in a fraction of the time.

That's what this offers: incredible creative freedom. Will other things be lost? Yes! Maybe ideas I would have had through writing it the old way will never happen. But that is what happens with every new technology. That does not make ChatGPT good or bad. It is a powerful new tool.
 

Clint_L

Hero
What works? This video from Corridor Crew's "Lawyer Explains Stable Diffusion Lawsuit (Major Implications!)" is my source. Followed by Google to see if it was true.

Restating, I am not a lawyer.
That is a specific case about a technology that deals with one type of AI. It is not going to come close to resolving the broad issues I raised. As I pointed out, many pieces of art that have an incredible amount of AI contribution are already copyrighted. The question isn't whether work done with AI can be copyrighted, but rather where lines should be drawn in terms of originality and methods for building the AI.
 

Jer

Legend
Supporter
I can get it produce a ton of iterations on different ideas. I can throw in my own writing whenever I want. I can tweak and massage and experiment. Artistically, I can let ideas build up far faster than I could writing on my own. And I can probably write a pretty cool guide, original to the world and specifically tailored to MY needs, in a fraction of the time.
Go for it! I suspect you're going to find that it's actually a lot more work than you think and you'll end up abandoning the ChatGPT once your own creative energies get flowing, but maybe it'll work better for you.

I say this because I started doing exactly that, was excited at first but quickly found out that what ChatGPT was giving me kinda stank and I was doing A LOT of editing and/or random restarting to make it sound even reasonably like something I'd be happy to put my name on, and stopped using it. It started out as a fun little exercise but rapidly became more work than just writing it for myself.
 

Asisreo

Patron Badass
Humans, on the other hand, have a complex system of inputs that include not just what we've read but also what we've experienced. And our emotional responses to these things. Yes if you want to get essentialist these are chemical reactions to the experiences that lead to different brain states, but we have them and they are an input that Large Language Models - which only have language - do not.
What's important to me, though, is if the inputs and memory barriers are the only thing stopping a "human" AI.

In other words, if we were reduced to only being able to interact with the world through reading or writing text, with no visuals, sounds, etc. And if our memory was nerfed to only remembering within a thread's worth of conversation, what would be the difference in the responses of ChatGPT and ourselves.

Another thing. ChatGPT isn't very original, but I don't think it's trying to be. I imagine that if ChatGPT sees a pattern across its input data, it will want to copy that pattern because it's being reinforced. Unlike humans, it's goal isn't to design something interesting or unique, it's just answering the prompt in the most human-sounding way possible.

But that doesn't mean a different AI can't be programmed specifically for novelty or engagement.
 



Jer

Legend
Supporter
What's important to me, though, is if the inputs and memory barriers are the only thing stopping a "human" AI.
This is an open question in AI research -whether "strong" AI is possible or not. The jury is still out. But LLMs are not that and may not even be a fruitful path towards getting that. The jury is still out on that too (though I'm in the skeptical side - I think it's likely to end up being a neat toy that can do some things very well but ultimately a dead end on the path towards strong AI).

In other words, if we were reduced to only being able to interact with the world through reading or writing text, with no visuals, sounds, etc. And if our memory was nerfed to only remembering within a thread's worth of conversation, what would be the difference in the responses of ChatGPT and ourselves.
I mean, yes, if you take away everything that makes us human and reduce us down to a state machine that gives the same performance as a GPT algorithm you'll get the same performance. It's kind of a tautology there.

I know what you're getting at - "is there something magical about humans such that an AI can't replicate us". And the answer to that is "the jury is still out" (see above). But I can tell you we ARE more than machines that collect statistics on the syntax of a language and repeat back convincing sounding text based on randomly perturbing our way through those statistics. If that was all we were entire branches of philosophy would never have been invented for starters. A large language model cannot analyze things, it can only generate text based on the distribution of words its discovered in the data it's trained on (which is why they can't really be stopped from lying either. "The sun is the source of its own light." and "The moon is the source of its own light." are both quite reasonable sentences for it to construct and the first one is only slightly more probable than the second absent any ability to do more than construct strings of words into a plausible syntactically correct sentence. And depending on the training set they may be equally likely. Or the second may even be more likely.)

Another thing. ChatGPT isn't very original, but I don't think it's trying to be. I imagine that if ChatGPT sees a pattern across its input data, it will want to copy that pattern because it's being reinforced. Unlike humans, it's goal isn't to design something interesting or unique, it's just answering the prompt in the most human-sounding way possible.
But this is actually something that is part of the basic idea of a large language model - it's a model that is built from basically collecting statistics across large datasets of text. So if you want true novelty you need to be thinking about a different algorithm. So this technology is not going to get better at it, it will only get better at generating realistic sounding text and keeping a consistent "train of thought" going as resources increase and it can keep a wider and wider context of the previous discussion it's had. What you'd want is a new breakthrough - a new algorithm that approaches the problem in a different way.

Now the LLM could be used as a front end to an algorithm that generates novel ideas - a way to express the ideas that it comes up with. That was the original purpose of LLMs at one point - to be used in tandem with another algorithm to help make the text generated read more like actual natural language. Using them by themselves is an artifact of researchers being somewhat surprised at how much of the meaning of what we say can actually be gleaned from the syntax that it has learned. (I'm actually not sure how well this research is generalizing to other languages right now - I haven't seen a lot of publications about non-English LLM algorithms. I should go looking I suppose.)
 

Asisreo

Patron Badass
I know what you're getting at - "is there something magical about humans such that an AI can't replicate us". And the answer to that is "the jury is still out" (see above). But I can tell you we ARE more than machines that collect statistics on the syntax of a language and repeat back convincing sounding text based on randomly perturbing our way through those statistics. If that was all we were entire branches of philosophy would never have been invented for starters. A large language model cannot analyze things, it can only generate text based on the distribution of words its discovered in the data it's trained on (which is why they can't really be stopped from lying either. "The sun is the source of its own light." and "The moon is the source of its own light." are both quite reasonable sentences for it to construct and the first one is only slightly more probable than the second absent any ability to do more than construct strings of words into a plausible syntactically correct sentence. And depending on the training set they may be equally
I don't think anyone thinks there isn't more to human language than what ChatGPT outputs. But those limitations theoretically can be overcome. It wouldn't strictly be an LLM, but if we're going for "more human," then we'd have to expand past that anyways.

Anyways, it's a bit off-topic on whether ChatGPT can make adventures.
But this is actually something that is part of the basic idea of a large language model - it's a model that is built from basically collecting statistics across large datasets of text. So if you want true novelty you need to be thinking about a different algorithm. So this technology is not going to get better at it, it will only get better at generating realistic sounding text and keeping a consistent "train of thought" going as resources increase and it can keep a wider and wider context of the previous discussion it's had. What you'd want is a new breakthrough - a new algorithm that approaches the problem in a different way.
We would need a new algorithm to imitate human's creativity, but maybe not insurmountably complex.

I mean, human creativity is also based on inputs and association. Even if the inputs are a few degrees apart, having an algorithm query similarities to two concepts and merge them together contextually wouldn't be impossible. Nor would taking how many times it's seen a concept and trying to put a twist on it. Although they might be pretty difficult to program in.
 

Epic Threats

An Advertisement

Advertisement4

Top