D&D General AI ranks D&D editions

[Snarf Zagyg]

So, you're saying it was trained on boosted articles from twitter/fb/google news and internet discussion boards?

hmmm..... now I want the AI to rank STAR TREK CAPTAINS!

 

[J.Quondam]

One of my favorite pagan and folklore writers just made a post about this. Apparently the #1 book under "celtic paganism" on Amazon right now is by "Mari Silva", who appears to be an AI-based writer or content farm, both from reviews of their text and the fact that they've put out 312 books in the last two and a half years.

Iirc, a few weeks ago, Facebook/Meta withdrew an online interface to a big science AI project, Galactica, in part because it was generating scientific papers, etc, that looked authoritative, but were completely bogus in terms of the fake "facts" they presented and/or citations they invented.

These AIs simply don't understand the difference between a legitimate text and a "yeah, that looks legit" text. And that's a massive problem because we human beings have similar bugs in our own brains which make us susceptible to confirmation bias, propaganda, and the like. This stuff can be used (and almost certainly is being used) to deliberately deceive, defraud, and otherwise misinform on a massive scale, for all sorts of nefarious ends.

 

[HomegrownHydra]

Proof that AI isn't replacing actual writers any time soon lol. Many of those things are...not remotely correct, and some of the most popular discussed features and criticisms aren't even mentioned.

But the same would be true for a response by a person. If you were to provide a single paragraph summary of each edition people would be highly critical that some of what you wrote is wrong and that you left out some of the most significant qualities.

 

[Vaalingrade]

hmmm..... now I want the AI to rank STAR TREK CAPTAINS!

1) The Doctor whenever he was left in charge*
2) Benjamin Sisko
3) Jean Luc Picard
No Others Found

*May be due to AI bias

 

[EzekielRaiden]

That text is frankly Turing complete, if you hadn't said it was AI I would never have known, absolutely looks like something a person would put together.

That's not really how the Turing test works, firstly. More importantly, very short stuff like this has been achievable since at least GPT-2, and I'm fairly sure the above is either GPT-3 or even the model coming after it (which may or may not end up getting called GPT-4.)

 

[Benjamin Olson]

That text is frankly Turing complete, if you hadn't said it was AI I would never have known, absolutely looks like something a person would put together.

Absolutely true, though I would say it looks like what an actual person with no interest in the subject, working on a deadline would say about it. It reads like what a journalist might give as background, in passing, or like the text of some clickbait listical. It has 'I was obligated to fulfill a word count" all over it.

Which will be perfect for this technology's future filling the internet with more terrible listicals and writing student papers.

 

[Levistus's_Leviathan]

I mean ... that's one way to look at it.

Another way to look at it is this- you now have freely available, publicly accessibly AIs that can generate text from prompts that look as if a human generated them. It may not be the best work out there, but it's better than a lot of high school level writing (not to mention the "foreign webpages" we see so often).

This is just the last couple of years, and freely available, and generated from a writing prompt BTW. Something that five years would not have been remotely possible.

Put it this way-

Three years ago, if someone suggested that AIs would be replacing artists in the next twenty years, I would probably have laughed.
This year, we are having serious conversations about ... AI replacing artists (illustrators, etc.) and the ramifications of that in the next few years.

Things are moving really really really quickly- and in a lot examples, we don't understand how these things operate ... just that, unlike a lot of other things, they are scalable.

I've recently become increasingly aware that a "robot apocalypse" where Ultron, Skynet, or the machines from the Matrix brutally take over the planet and kill/enslave all humans is pure fiction and almost definitely not going to happen. Robots will take over the world, but not like that. The robot revolution won't be fast or bloody, it will just be the result of them being better at our jobs than we are, and thus us being replaced by them.

It's a bit distressing, even if it's probably not going to happen in the next decade or two. Eventually we're all going to become Luddites.

 

[Charlaquin]

I've recently become increasingly aware that a "robot apocalypse" where Ultron, Skynet, or the machines from the Matrix brutally take over the planet and kill/enslave all humans is pure fiction and almost definitely not going to happen. Robots will take over the world, but not like that. The robot revolution won't be fast or bloody, it will just be the result of them being better at our jobs than we are, and thus us being replaced by them.

It's a bit distressing, even if it's probably not going to happen in the next decade or two. Eventually we're all going to become Luddites.

Much like how climate collapse won’t be an apocalyptic event, just a gradual process of life getting a little bit worse. Both things are cases of boiling the frog slowly.

 

[Charlaquin]

This is largely pretty solid, though obviously missed that AD&D 1e was far from the original edition of D&D. Also pretty strange that it claims 2e originated character classes, levels, and alignment.

 

[J.Quondam]

I've recently become increasingly aware that a "robot apocalypse" where Ultron, Skynet, or the machines from the Matrix brutally take over the planet and kill/enslave all humans is pure fiction and almost definitely not going to happen. Robots will take over the world, but not like that. The robot revolution won't be fast or bloody, it will just be the result of them being better at our jobs than we are, and thus us being replaced by them.

It's a bit distressing, even if it's probably not going to happen in the next decade or two. Eventually we're all going to become Luddites.

Yeah. In the end, AI are just tools, so how it all plays out comes down to how those tools are used. Of course, humanity being what it is, those tools are at least as likely to be used for bad thing as for good.
And also for unabashedly stupid things.

 

[Vaalingrade]

Yeah. In the end, AI are just tools, so how it all plays out comes down to how those tools are used. Of course, humanity being what it is, those tools are at least as likely to be used for bad thing as for good.
And also for unabashedly stupid things.

Robots will kill us all by hitting an extra GOTO 10 and forget to feed us.

 

[HomegrownHydra]

Absolutely true, though I would say it looks like what an actual person with no interest in the subject, working on a deadline would say about it. It reads like what a journalist might give as background, in passing, or like the text of some clickbait listical. It has 'I was obligated to fulfill a word count" all over it.

Which will be perfect for this technology's future filling the internet with more terrible listicals and writing student papers.

In other words, it reads like it was ripped from Wikipedia. And that's its best responses. It's not-so-good and outright bad responses are even worse.

 

[Dausuul]

That text is frankly Turing complete, if you hadn't said it was AI I would never have known, absolutely looks like something a person would put together.

I know you meant the Turing test, but that got me curious, so I asked the GPT-3 chatbot:

>> Are you Turing complete?

No, I am not Turing complete. I am a large language model trained by OpenAI, and I am designed to assist with a wide range of tasks, including answering questions, providing information, and generating text. However, I am not capable of executing arbitrary computational tasks like a Turing-complete system. I can only operate within the capabilities and limitations that have been specifically programmed into me.

(I think it's lying, though. Somebody already figured out how to make the chatbot mimic Linux, complete with the ability to write and run Python scripts, and Python is Turing complete. Maybe the Python simulation would fail if you pushed it too far, but I bet with the correct series of prompts, you could make the chatbot into a Turing machine.)

 

[Blue Orange]

Python? I've seen it write a Monty Python skit somewhere on the Internet...

 

[GreyLord]

1) The Doctor whenever he was left in charge*
2) Benjamin Sisko
3) Jean Luc Picard
No Others Found

*May be due to AI bias

Well...maybe on that basis...I asked the Hal597 what it thought were the best Captains and it said...

1) The Doctor (when he was in charge)
2) Data
3) The EMH mark 2
4) The others were merely big bags of water...not captains.

Next I asked it why the other AI may have ranked the editions like it did.

Hal597 had a simple answer.

Whatever gave back the most hits on the internet/where it searched on sites via it's search method was how it ranked. Thus it got the most hits for 5e so obviously that was the best. Interestingly enough, it got more hits for 3e than 4e so that was next. Then the hits came for 4e and then 1e and then 2e.

Very simple for it to figure that the more popular ones were the higher ranked ones. At least according to it's search parameters.

 

[Sepulchrave II]

4. Dungeons and Dragons Original Edition (D&D 1e) - This is the first edition of the game, and is known for its simplicity

I see the AI wisely chose to ignore around half of the rules in the DMG.

 

[Snarf Zagyg]

I see the AI wisely chose to ignore around half of the rules in the DMG.

No one (even an AI) reads the DMG!!!!

 

[Charlaquin]

I know you meant the Turing test, but that got me curious, so I asked the GPT-3 chatbot:

>> Are you Turing complete?

No, I am not Turing complete. I am a large language model trained by OpenAI, and I am designed to assist with a wide range of tasks, including answering questions, providing information, and generating text. However, I am not capable of executing arbitrary computational tasks like a Turing-complete system. I can only operate within the capabilities and limitations that have been specifically programmed into me.

(I think it's lying, though. Somebody already figured out how to make the chatbot mimic Linux, complete with the ability to write and run Python scripts, and Python is Turing complete. Maybe the Python simulation would fail if you pushed it too far, but I bet with the correct series of prompts, you could make the chatbot into a Turing machine.)

Fun fact, it’s possible (albeit very convoluted) to make a Turing machine inside a game of Magic: the Gathering.

 

[M_Natas]

Everybody can get an account at beta.openai.com and try out the AI.

The story it writes I would say are High School Level Niveau.
Here are some examples what you could try with it:

Topic: plains in the shadowfell.
A list of 10 fantasy dungeons and dragobs encounters:

1. The Shadowfell Mire: A vast swamp filled with deadly creatures and dark secrets.
2. The Gloomwood: An ancient forest full of dark magics and creatures.
3. The Valley of the Dead: A desolated valley full of undead monsters and ancient tombs.
4. The Choking Wastes: An inhospitable wasteland populated by savage beasts and nomads.
5. The Tower of Bones: An abandoned keep full of undead monstrosities and dark secrets.
6. The Ruins of Sharn: A city of ruins full of lost secrets, powerful artifacts, and dangerous monsters.
7. The Iron Mines of Karrnath: An ancient mine filled with unimaginable wealth and deadly traps.
8. The Tomb of the Sea Witch: A mysterious underwater tomb filled with undead horrors and ancient secrets.
9. The Dark Halls of the Shadow King: A labyrinthine dungeon filled with powerful creatures and artifacts.
10. The Tower of the Black Sun: An ancient tower filled with secrets, monsters, and powerful magic.

Topic: unique Monsters with long random pseudolatin names and strange lovecraftian features.

A list of 5 different Monster with 2-sentence physical descriptions, 1 sentence strength, 1 sentence weakness, 1 sentence nature and 1 sentence behaviour:

1. Xrixacuxus: A giant, skeletal humanoid with two large, scaly wings sprouting from its back. Its wide mouth is filled with razor-sharp teeth, and its eyes glow a deep purple. Its strength lies in its ability to fly at incredible speeds and its razor-sharp claws. Its weakness is its vulnerability to bright light and sound, which can disorient it. Its nature is mysterious and unpredictable, and it loves to cause chaos in its wake. Its behaviour is to swoop in and surprise its victims before quickly flying away.

2. Yithirix: This creature is covered in thick, slimy tentacles that stretch out from its body and extend for miles. Its eyes are hidden deep beneath a slimy mask, and its mouth is filled with razor-sharp teeth. Its strength is its ability to manipulate its environment, creating illusions and manipulating the minds of those around it. Its weakness is its vulnerability to loud noises, which can cause it to become disoriented. Its nature is mysterious and chaotic, and it loves to sow confusion and terror. Its behaviour is to remain hidden until it can find the perfect opportunity to strike.

3. Zordalix: This giant, four-armed creature has a head resembling a giant manta ray. Its eyes are filled with an eerie yellow glow, and its long tentacles can reach out for miles. Its strength is its immense physical strength and its ability to manipulate its environment. Its weakness is its vulnerability to bright light, which can cause it to become disoriented. Its nature is unpredictable and chaotic, and it loves to cause destruction and mayhem. Its behaviour is to remain hidden until it can find a way to cause maximum chaos and destruction.

4. Dizixal: A giant, four-legged creature with a long, snake-like body and a large, spiked tail. Its eyes glow a deep red and its mouth is filled with razor-sharp teeth. Its strength is its agility and speed, and its ability to strike quickly and accurately. Its weakness is its vulnerability to bright light, which can disorient it. Its nature is chaotic and unpredictable, and it loves to cause destruction and mayhem. Its behaviour is to hide in the shadows and wait for the perfect opportunity to strike.

5. Krakulix: This gigantic, hulking beast has four long, spindly arms and a large, scaly body. Its eyes glow a deep blue, and its mouth is filled with sharp, jagged teeth. Its strength is its immense physical strength and its ability to tear through almost anything. Its weakness is its susceptibility to bright light, which can disorient it. Its nature is chaotic and unpredictable, and it loves to cause destruction and mayhem. Its behaviour is to rampage through whatever it can, leaving destruction in its wake.

If combined with Stable Diffusion or Midjourney you could make a full Monster Manual with Illustrations in Hours ^^.
Some things are repeated, but you can tweak the AI to not repeat itself so much.

 

[M_Natas]

And here is a Horror Story written by the AI:

The haunting began shortly after my mother passed away. I would wake up in the middle of the night to find her standing at the foot of my bed, looking at me with a sad, longing expression. It was as if she were trying to communicate something to me, but I couldn't understand what she wanted.

I tried to ignore her, but it was difficult. She would follow me around during the day, appearing in mirrors or windows when I least expected it. And at night, she would visit me in my dreams, always with that same sad, longing look on her face.

One night, I finally asked her what she wanted. "I want you to marry," she said. "I want you to be happy."

I told her that I didn't want to get married, that I was happy the way I was. But she wouldn't listen. She said that it was my duty to carry on the family name and that she wouldn't rest until I was married.

The haunting continued, and my mother's presence grew more and more oppressive. She began to appear even when I was awake, and her visits became more frequent and more insistent. Finally, I gave in and agreed to get married.

It wasn't long after that when I realized that my mother's spirit had taken possession of my wife's body. She would often say things that my mother used to say, or do things that reminded me of her. It was as if my mother were living through my wife.

The final straw came when my wife gave birth to our son. As soon as he was born, my mother's spirit left my wife's body and entered into his. Now, my own son is haunted by his grandmother's spirit, and I can only watch helplessly as she tries to control his life...

And here and AI outline for a D&D Adventure:

The adventure begins with the party's arrival at a small village called Greenest. The village is being attacked by a group of kobolds and the party is quickly drawn into the fray. After dispatching the kobolds, the party is approached by a representative of the village who asks them to help protect the village from further attacks.

The party agrees to help and sets out to patrol the village perimeter. After a few hours of boredom, the party is attacked by a group of giants. After a tough battle, the party defeats the giants and is hailed as heroes by the villagers.

The party is then approached by the village elder who asks them to investigate some strange happenings in the nearby cave. The party agrees and sets out for the cave.

Inside the cave, the party encounters a group of goblins who are quickly dispatched. Further in, the party encounters a strange creature that is immune to all damage. After a long and frustrating battle, the party is forced to retreat.

Back in the village, the party rests and regroups. They then set out again for the cave, this time better prepared for the creature. After a tough battle, they finally manage to kill it.

Further into the cave, the party finds a group of kobolds who are mining for something. The kobolds attack the party, but are quickly dispatched. The party then finds a strange magical ore that is emitting a strange aura.

The party decides to take the ore back to the village elder to see if he can identify it. On the way back, the party is attacked by a group of bandits. After a fierce battle, the party defeats the bandits and returns to the village.

The elder is unable to identify the ore, but he does know of a wizard who might be able to help. The party sets out for the wizard's tower.

Inside the tower, the party encounters the wizard who is guarded by a group of golems. After a tough battle, the party defeats the golems and the wizard. The wizard is able to identify the ore as a powerful magical substance.

The party then decides to take the ore back to the village to sell it. On the way back, the party is attacked by a group of kobolds. After a quick battle, the party dispatches the kobolds and returns to the village.

The party sells the ore to the village elder for a hefty sum of money and is hailed as heroes once again. The adventure ends here, but the party can stay in the village to help protect it from further attacks or set out to find more adventure.


The above is a basic outline for a dungeons and dragons adventure for a party of level 2 characters. You can use this as a starting point and flesh it out as you see fit.

Battle heavy ... at the moment you can use the AI to help you brainstorm ideas. But it really gets better. Even one or two years ago it would have been unthinkable to create such a consistent text over several paragraphs.