[latexr]

The repetitiveness in video game dialogues is a feature, not a bug. Amongst other things, it allows you to re-retrieve information and hone in faster on what’s story and what’s relevant progression. Having each character invent their own inconsistent sloppy backstory whenever you talk to them is not a positive, it’s not good immersion when every character is a chatbot that can inadvertently give you story beats you shouldn’t be aware of yet or you missed some crucial bit of information but no one talks about it anymore (or worse, never did). In that world, those games would be made popular by people breaking the LLMs in funny ways, not the gameplay itself.

[8n4vidtmkvmk]

I don't think it can give you story beats you shouldn't be aware of yet. Those beats wouldn't be fed into the prompt until the event happens. LLM can't spit out what it doesn't know.

It might indeed fail to reveal something it should but even that i think is unlikely if the harness steers it hard enough.

I think it could be fun. If you're always given 4 choices of what you can ask the NPC then your choices can be too obvious. If its open ended then you have to think a little what to say and ask.

[nkrisc]

Why couldn’t an LLM accidentally spit out story beats if they plausibly follow from the context and the player’s input into the conversation?

[hdjrudni]

What "context"? If it's coming from the player's input, then the LLM isn't spoiling anything.

e.g. let's say an important character dies in your game but that hasn't happened yet in this point in the story. You're talking to some NPC. That NPC can't possibly spoil that that character is going to die because the developer wouldn't feed that in as context. The NPC doesn't "know" the character is going to die. You, as the player, might be able to convince the NPC that that will happen and it might respond accordingly, but it won't just randomly divulge that by accident.

[td2]

Or worse, what if the story of the game was already part of the training data

Like a remake of a game

[hdjrudni]

This one is a fair point... if all the characters have distinctive names then NPC can plausibly become aware that it is a character in that game and spoil things. I don't know how to stop that, short of training a clean model from scratch, but that seems a bit much for a game.

[coinfused]

Hadn't thought about it that way, but when I look back at the mostly single player/story-based games I play I agree!

[scoot]

> it’s not good immersion when every character is a chatbot that can inadvertently give you story beats you shouldn’t be aware of yet or you missed some crucial bit of information but no one talks about it anymore

What you're describing isn't bad dialog, it's bad interaction design.

I think your mental model might be of a single session with zero state, and no bounds on topics of conversation outside of the character's backstory. That isn't close to how this would work. A little understanding of how the game currently operates and some imagination, and you'll see how it could be improved further without degrading gameplay.

> those games would be made popular by people breaking the LLMs in funny ways

Because making the game do funny things didn't happen with RDR2, or any other game, device, or indeed humans (there are whole genre built around making people do or say "funny" things).

[latexr]

Perhaps try to steel man the argument. Your entire response is just one large condescendingly wrong straw man.

> What you're describing isn't bad dialog, it's bad interaction design.

I didn’t say it was bad dialogue. It should be pretty obvious that’s not the argument since I talked in terms of feature VS bug.

> Because making the game do funny things didn't happen with RDR2, or any other game, device, or indeed humans

Again, not at all what was said. Of course those things happen, and of course I know that. The clue is in the fact that I brought it up, which can be ascertained by reading the comment and engaging with it in good faith. The point was that becoming the focus.