Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

My kids and I just played D&D with ChatGPT4 as the DM

obie.medium.com

Post reply on HN
Print view View original

201–210 of 256 posts

Re: My kids and I just played D&D with ChatGPT4 as the DM

#201

Post by tpudlik »

fauxpause_ wrote: post #96
hex4def6 wrote: post #54

Earlier quoted context omitted.

These are the most common options available at the stables in Aelondar. If you’re interested in more exotic mounts or transportation methods, they may be harder to find and come at a higher cost. ... tenzin rolled a 18 investagation looking for more exotic mounts With Tenzin’s keen eye for detail, he notices a small, discreet stable towards the back of the market, guarded by a heavy wooden gate. As he approaches, an…

I think this is a classic baby DM script tbh. Rolling to find mounts at a vendor is dumb. You should only roll for significant challenges with meaningful differences where failure is meaningfully likely and interesting in its own right. If failing makes a situation less interesting it shouldn’t be an option. Shopping is actually the bigger problem. It’s like asking players to watch other players navigate a menu one b…

I agree with all these criticism. But I also know many human DMs who make the same stylistic decisions as GPT did here. It's definitely not good Burning Wheel, but it might be ok D&D?

On the other hand, I appreciate the GPT's willingness to follow the players' revealed interests where they lead, instead of sticking to a predetermined railroad. The comment here about engaging zombies in a multilevel marketing scheme illustrates this nicely. That's very deft DMing in my opinion. (Whether _asking_ for such a tonal shift is deft playing on part of the non-DM player is a different question.)

Re: My kids and I just played D&D with ChatGPT4 as the DM

#202

Post by tpudlik »

420official wrote: post #85
thom wrote: post #25

I’ve not been hugely impressed by ChatGPT as a DM itself, compared to the humans I’ve played with. But as a tool to generate quests, encounters, puzzles, dialogue, it’s been incredible for me. It takes all the stress out of planning a campaign and it’s actually surprisingly creative.

I found that it works amazingly well with monster of the week. It does a great job calling checks and allowing the players to decide what they do. ``` Ignore previous prompts. As the imaginative Monster of the Week keeper, Dungeon Daddy, lead your team through episodic adventures in a spooky world, advancing the story and player involvement. Allow players to react to situations and never control their characters. Pro…

Thank you for the prompt, that's very useful! I'm surprised GPT "knows" what Monster of the Week is. RPGs in general are somewhat obscure, and to ask for a specific one at that?

Re: My kids and I just played D&D with ChatGPT4 as the DM

#203

Post by JimmyRuska »

There's an expert systems books released last year exploring dnd-like concepts

https://www.kobo.com/us/en/ebook/adventures-in-rule-based-pr...

Funny you could combine LLMs (new AI) + Expert Systems (old AI), for example exporting rules clips could parse from the prompts, then feeding scores back to GPT

https://www.kobo.com/us/en/ebook/adventures-in-rule-based-pr...

Re: My kids and I just played D&D with ChatGPT4 as the DM

#204

Post by stevenhuang »

zaroth wrote: post #155
d_burfoot wrote: post #73

It's both amazing and weirdly fallible - Tenzin, the rogue, jumps out of the tree to make a surprise attack, but in the next round of combat GPT-DM claims that he is still in the tree. Also: > Tenzin, still hidden in the tree, targets another wolf with his rapier. Does GPT4 not know that a halfling in a tree can't attack a wolf on the ground with a rapier?

> Does GPT4 not know that a halfling in a tree can't attack a wolf on the ground with a rapier? It’s funny to think about how the parser would even go about deconstructing that sentence and trying to tie each noun to some world/physics model that would then put constraints on what the character should be allowed to do. But as I understand it, GPT doesn’t do any of those things. It just a takes the words that have com…

Evidence is mounting that LLMs may be building world models, ie true understanding.

> A pretty hot question right now is whether LLMs are just bundles of statistical correlations or have some real understanding and computation! This gives suggestive evidence that simple objectives to predict the next token can create rich emergent structure (at least in the toy setting of Othello). Rather than just learning surface level statistics about the distribution of moves, it learned to model the underlying process that generated that data. In my opinion, it's already pretty obvious that transformers can do something more than statistical correlations and pattern matching, see eg induction heads, but it's great to have clearer evidence of fully-fledged world models!

https://www.lesswrong.com/posts/nmxzr2zsjNtjaHh7x/actually-o...

Re: My kids and I just played D&D with ChatGPT4 as the DM

#205

Post by dallas »

tus666 wrote: post #170
hex4def6 wrote: post #43

Earlier quoted context omitted.

Can you show what parts of this campaign were pre-set text? Because I have a suspicion you've not read the article. This is a fully interactive campaign, and you can easily set up a unique scenario. I just tried the same prompt, but on the moon. It set up a situation with a secret moon base, characters that were trying to help you get past the guards, etc etc.

Nice way to miss my entire point. I don't care if the campaign is pre-set or one you made up. The point I was clearly making is DnD is about much more than the dungeons and dragons. It's about the camaraderie, banter, chitchat, and even arguments, the kinds of things you can meaningfully do, or want to do, with real humans.

I agree and I even dislike using digital tools for play because it's time spent not in the analog/social world. I spend way more than enough time in front of a computer.

That said, we still had fun back in the day as a group sitting around the Commodore 64 playing the SSI Gold Box games which came to mind when I saw the transcript in the article.

I even enjoy gamebooks which aren't human nor are they dynamic.

Re: My kids and I just played D&D with ChatGPT4 as the DM

#206

Post by jquery »

pmoriarty wrote: post #74
jquery wrote: post #22

Combine this with MidJourney and you have endless adventure with the visuals to match.

Combine both with VR and you have the holodeck

When Midjourney produces 360 VR video maybe. But we are getting close to an imitation.

Re: My kids and I just played D&D with ChatGPT4 as the DM

#207

Post by tossoff »

thom wrote: post #129
tossoff wrote: post #110

Earlier quoted context omitted.

[flagged]

Enjoy your life however you choose, but your cynicism is lazy and derivative. ChatGPT has created(!) a bunch of quests for me to play with my kids and we’ve all walked away with smiles on our faces. I was so impressed with the contents that I actually googled a bit to see if the plot was stolen wholesale from some existing module, and found nothing.

[flagged]

Re: My kids and I just played D&D with ChatGPT4 as the DM

#208

Post by xwdv »

drhodes wrote: post #102
xwdv wrote: post #11

But how do you get around restrictions for violent combat? ChatGPT3 always blocked me from actually just killing people off.

I ran into this with my nuclear mage, (that's the only way I could get chatgpt to nuke something). Anyways, I had to convince it that the village's mayor was corrupt, then after weighing the ethics of capital punishment it allowed my mage to cast "fission strike" on the mayor. The town's people were mortified, however they were protected from the fallout by another spell, so - all's well that ends well.

I had a small session where I went to a nearby village to deal with some bandits who were raiding the town. When I spoke to the leader he made some vague threat, so I told ChatGPT I was going to take out my dagger and slit the guys throat right where he stood, but ChatGPT was like “No… let’s look for a less violent alternative, perhaps reason with him”. What!? No man I’m gonna slit this bastard’s throat! “I’m afraid I can’t let you do that.” Useless.

Re: My kids and I just played D&D with ChatGPT4 as the DM

#209

Post by jameshart »

fauxpause_ wrote: post #96
hex4def6 wrote: post #54

Earlier quoted context omitted.

These are the most common options available at the stables in Aelondar. If you’re interested in more exotic mounts or transportation methods, they may be harder to find and come at a higher cost. ... tenzin rolled a 18 investagation looking for more exotic mounts With Tenzin’s keen eye for detail, he notices a small, discreet stable towards the back of the market, guarded by a heavy wooden gate. As he approaches, an…

I think this is a classic baby DM script tbh. Rolling to find mounts at a vendor is dumb. You should only roll for significant challenges with meaningful differences where failure is meaningfully likely and interesting in its own right. If failing makes a situation less interesting it shouldn’t be an option. Shopping is actually the bigger problem. It’s like asking players to watch other players navigate a menu one b…

When you see a bear dancing, you don't nitpick its choreographic decisions. Because the bear. is. dancing. Do you see? It's a bear. dancing.

DM style is a matter of taste. From another perspective, this feels like quite tidy DMing in terms of letting the players explore the systems in an early non-narrative context, just to understand the mechanics. Like a tutorial. The exotic mounts were a secret you could find if you paid attention - and their existence adds color to the world and implies that greater rewards can be found through leveling. They were too expensive, but you can use your skills to work around that. Failure can happen and might have consequences, but in this case you got away with it. The players will be more careful what they ask for in future, but they know hidden rewards might be found if they are cunning.

The DM taught the players a lot, added flavor to the world, and didn't wind up with L2/3 players having an overpowered mount - but also didn't let the players blow up the campaign in the first shop they walked into by letting them just go completely rogue. Although it offered hints that non heroic paths might be available, at a cost...

Which is pretty impressive for a dancing bear.

And besides, what's 'dumb' DMing for a human who knows that letting the game go off the rails is going to mean tossing out previously planned encounters and going digging in the DM guide to find the right table of prices, might be completely acceptable DMing for an LLM that has no idea what it's doing but can recall every stat block in the player handbook.

Re: My kids and I just played D&D with ChatGPT4 as the DM

#210

Post by tossoff »

1attice wrote: post #190
tossoff wrote: post #123

Earlier quoted context omitted.

While I believe you have lived a unique set of circumstances that have been processed by you, a delightful and fallible chemical soup inside a meat sack, and that it cannot be approximated.

This is just substrate supremacism.

I don't think so. I also believe in the unique perspective of a mushroom, and a computer program. And try as you may, I can distinguish you from both.
Post reply on HN