Hacker News new | ask | show | jobs
by parineum 1189 days ago
I've been trying to make it be a DM for a while now. It works seemingly well for a while but it's making everything up on the fly, which is fine as long as there's not state that needs to be maintained/remembered. Once you start trying to get it to do combat, it seems like it's working pretty well but eventually you realize that it's just making shit up behind the scenes. It'll tell you there are 4 goblins ambushing you and then you can ask it how far away they all are and it'll list three. You ask what happened to the fourth one and it'll say I'm sorry, there were only 3. I was mistaken before.

If it lists the properties of an item that you might want to buy in a shop, you can ask it to describe it twice and it'll describe two completely different items.

It's really cool and it's pretty (seemingly) creative but it can't actually run a game for you. You can have it as an assistant DM though, that works pretty well. You can have it write a story for you ahead of time and then keep it around during the game to ask it to elaborate on things you didn't anticipate on the fly. Like, "generate DC tiers for a level 3 party investigating strange writing on a wall" will give you a good breakdown and some results that you'll have to bend to be consistent in your adventure but it's pretty helpful.

That's probably not really necessary if you're an experience DM but the DM for the group I play with is pretty new (as are we all) so it's been really cool to have it around. It's also pretty good at answering questions we have but it's confidence when it's wrong makes it so it's not that helpful really because we still have to check it.

5 comments

You should put a blog/site up with some examples.

"GPT being the worst DM ever" sounds hilarious.

"I attack the goblin." "What goblin?" "The goblin you just said was there." "I'm sorry, I was mistaken. It's actually a Beholder."

I think this could make for a hilarious animated series. Kind of an AI-generated mashup between HarmonQuest[1] and DrunkHistory[2]

[1] https://en.wikipedia.org/wiki/HarmonQuest [2] https://en.wikipedia.org/wiki/Drunk_History

So you’re complaining it’s not smart in a way it was explicitly designed not to be (keep too long a context) so it doesn’t take over the world..
No. It's much worse than that. It doesn't remember what it just said the message before.

The thing I don't understand about it is that it works pretty great for a while but, eventually, it starts acting erratically, forgetting things it knew, not following instructions, etc. It's not that it forgets old things or can't learn new things, it just becomes dumb.

Maybe that's what you're talking about but I don't think AGI is going to have the memory of a goldfish.

I wonder if you'd get better results with a narrative-tuned tool like Sudowrite - although Sudowrite is currently limited to GPT3.5 and below.
Have you noticed any improvements with GPT-4 regarding the continuity and persistence if story and assets? In unrelated areas that feel similar I've noticed GPT-4 keeping track a lot better.
Context windows on GPT are still really small for the amount of tokens that would be generated in a story.