No Stupid Questions

First of all, I'm going to replace AI with LLM, since that's probably what you meant.

There are 2 distinct questions asked in this post:

1. Why not use LLMs to provide different levels of automation? (Like, manual, medium, auto)

Answer: you don't need LLMs for that. You can just code it in like any other feature. It's not particularly hard, game developers know how to do it since they are used to programming automation for NPCs.

2. Why not use LLMs to procedurally generate NPC dialogue?

Answer: games are primarily a form of art. NPC dialogues are written with a purpose. Different characters have different personalities. Some dialogues are meant to drive the plot. Other dialogues are meant to teach the player how to play. Others are meant to show the player things that they may have missed, or things that are interesting.

Procedural dialogues removes all the control from artists. They would all be generic npc n#473, with the "personality" of the LLM, maybe slightly varied if the developer writes a different prompt for each character.

Procedural dialogues would have the same issues as procedural world generation or photorealistic graphics, it would just not be interesting.

There is a practically infinite amount of Minecraft worlds, yet they all feel the same way. The thing that differentiates a Minecraft world from another is that which the player has built. The only part of the world that wasn't procedurally generated.

There is a great amount of photorealistic games. And they all look very similar. You may only distinguish one from another by looking at their handcrafted worlds or their handcrafted characters. But not by staring at a wall. You can stare at a wall in non-photoreslistic games and know what game it is.

So if you put procedurally generated dialogues, no one will read them, since you'll be bored by the time you read the same thing being said by 5 different NPCs from 5 different games.

Have you ever tried to run an LLM locally? It makes CPU usage go way up, uses a lot of RAM, etc. It would tank game performance and/or require beefier PCs.

Games already have had AI for a long time, but the kind of AI you're talking about would be far more computationally expensive than what they currently use.

AI in games (using code for entities to make non-player decisions) is about being good enough, cheap enough. It's just like how games determine their physics. The existence of large scale "black box" AI like OpenAI does not reflect what's good or cheap. It can't play chess. You think it's going to understand The Sims and make reasonable choices in that system?

They've already created well tuned system to give your Sims in obtaining their needs. It leads to you having to manage the chaos, and that's what the fun is. To better hone that is to have the AI play the game for you. And even that, if efficiency of play is the goal, is better done by TASbot and machine learning.

That generic black box style of AI like popular LLMS is like creating a hammer. Now everyone is treating every problem like nails. AI decisions making in games is like washing windows; don't use a hammer.

The problem is that "AI" is a poorly defined, very vague, and widely used term. Most people here have assumed you meant LLMs because everyone pitches those as ways to solve everything. "Oh, irer up an agent, give it instructions, and let it make requests that are context dependent". Then, like everyone says here, that usually turns into people testing boundaries and breaking your game. So that makes it both "not good enough" and "not cheap enough".

Now, look at AI with the term "machine learning" in mind and it's different. Games like ARC Raiders use machine learning to teach NPCs movement behavior, and to train AI voices like Siri so they can't add things without further paying people. They think that up-front investment is worthwhile. But those are both far cries from "uploading it to Claude or ChatGPT and see what happens". Especially when you would have to teach that black box AI your system anyway, for it to use it. And you're already doing that with current "good enough, cheap enough" bespoke methods, for much cheaper, and they're good enough.

You would have to design the game around an LLM, not just drop one into existing games.

It might be cute for the guards in Skyrim to have unique dialogue, until one of them denies the Holocaust or says feminism is cancer.

What value would it add to the game?

• LLMs are computationally expensive
• Replacing voice actors with AI means making dialogue worse
• Replacing writers with AI means making the story worse

At the end of the day AI is mostly a marketing term for LLMs and LLMs just aren't that useful in most games, they just average out a dataset to autocomplete a response, that autocompletion is worse than what a human would have written.

We saw with procedurally generated worlds that it takes a lot of effort to prune what is generated to make the game interesting.

There are particular subgenres of games and applications where LLMs might be useful though.

I have heard of some people experimenting with it, e.g in a stardew valley mod to allow you to have actual conversations with the characters.

Because fuck AI, that's why.

I think the Where Winds Meet tried this, right? The NPCs ended up saying anachronistic things and making travel itineraries for Beijing or something.

We do use AI in videogames, and have for multiple decades (with varying levels of sophistication).

Have you ever talked with an AI? It sucks.

If they used it for NPC dialogues there would be a non-zero chance they say something inappropriate, and controversy happens.

I'd love to see it being used by enemies so they're challenging without cheating, though.

It would need to be cloud-based, or otherwise require a lot of RAM

Because the kind of Genrative AIs which would be worth puting in a game (smaller ones) have two drawbacks for the hype train :

-you can't promise an AGI which would justify the govt putting mbillions in your company in order to stay "competitive"

You can't create a feedback loop of finance with nvidia and the like because your company wouldn't need such computational power then.

There is a game called Whispers from the Star which uses an LLM to run the script. It's pretty much a fancy choose your own adventure book. It's pretty shit.

https://youtu.be/zDa4l18z9z8?t=626

It would suck.

People have tried this a bit and it doesn't work well. Remember that most games have some sort of plot which needs to move forward without deviating too far and this is not easy to manage with AI. AI systems are predictive text tuned up, so they tend to wander in the conversation and this can be disastrous for something like a video game.

The world is there to support the illusion but also to direct the player to game material. An AI agent going off on a tengent about some random thing that kind of fits the world could lead to users running around wasting their time and being frustrated.

Add to that the risk of the AI system stepping into awful places like reproducing Nazi ideology and it is a nightmare for developeds. Imagine getting your game rated when it can randomly start telling your character not to worry about saving those people over there because their skin tone is darker and that makes them less than human.

Now as a tool for building scripts quickly? Maybe, but it does produce slop now and if that will change I cannot predict when. Maybe it could be used as part of the process but I think it is so toxic now I would not bet on it. I also think it should be labeled as the use of AI comes with moral issues around the environmental impact and theft of content from other people. If a game has AI generated content I won't be playing it, and I am not alone. Just the push back from audiences could be enough to discourage the use of AI systems.

Now on the other hand using a neural network design for making character behaviours more believable, for example using a series of needs and having the algorithm decide what to do next and so on, that could be cool, but we have that already and it isn't considered AI.

Despite being free/cheap to use right now, AI is expensive to run in terms of things like water and electricity. The companies that own the datacenters that perform the AI operations are running at a loss because they want to capture public trust and market share. Hence, no one wants to power a game with AI, when the people playing the game would just see it as a seamless advancement in game mechanics.

Also, no one wants to appeal to gamers directly, because they aren't a good demographic to have singing the praises of your product. Steve the fortune 500 CEO, and Maria the director of the state DMV, will not be enthralled by Caleb the racist 14 year old's product endorsement.

Finally, we've found that it us really hard to put effective guardrails on LLMs. So any company that did this would be risking Caleb posting a video online where their game is used to display or discuss lewd sexual acts, leading to bad PR.

Are you willing to put in an API key and pay money for interactions with an LLM?

It’s not really a one time cost. And I don’t know if devs really want to take on that expense.

I heard about a Chinese rpg that did something similar. The conversations were wide open, and instead of clicking through limited dialog choices, you had to type your responses. You get some guidance on what the purpose of the conversation is, but that’s it. Like: “cheer this person up!”

I think it’s a cute idea but ultimately too unpredictable using the current generation of LLMs.

IMO AI is better used as a game design tool than something running live in game. I remember running around so many open world games where it was obvious you had left the area you were meant to be in. Suddenly there’s few monsters, no quests or NPCs, and the least thought given to foliage and landscape decisions. BORING. I feel like that’s a great use of AI - create a non-critical landscape players can continue to explore, even if they won’t make any progress on the main quest/story lines.

A game studio isn’t going to pay designers to create rich experiences in unnecessary parts of the world, but they should be willing to pay designer to review a region like that and get it into the game.

You can not cage llm. They will break out at some point, it's proven again and again.

(it can have its uses, but this idea will run rampant with time - except of course that is the point, it could be awesome)

Why would we?

I saw someone play this game, Ai2U on a livestream recently.

You wake up in a cute girl's home who's eager to keep you by her side! Engage with thematic stories, puzzles, and unique AI NPCs who'll go to any lengths to protect you—even when it means contradicting themselves. Bask in meet-cutes or brace for chaos if you try to escape.

Basically, you have to vocally speak with this AI anime girl that is obsessed with you. She has you basically trapped and you some how have to convince or trick her into letting you leave.

The whole game is unhinged but it's a pretty fun example of an LLM being used in a game.

Imagine a game like “the sims” where you can adjust how autonomous the sims you control are. I could see Ai being used to control that.

So, Inzoi?

I saw someone mod Skyrim to have Lydia do that, looked pretty promising. There's also a series where AI Lara Croft is playing old tomb raider games with commentary in her voice and everything, though I heard it's not 100% AI