The tool calling part might be doable (though I've personally struggled to get it working passably with local models), but if the goal is to tell a compelling story or create an interesting experience, especially if doing so in a very open ended way, that isn't trivial. The only LLM based game I've personally played that seemed good was mostly on rails and partially scripted, most of them just aren't very interesting to play, because the model doesn't have a good idea where it's going with anything and is often not very creative, the stuffy personality of the instruct model seems to infect the dialogue and apparent thought process of the characters. For a specific example I'd recommend watching streams of the game Suck Up, which has a genuinely cool concept and solid execution, but you can see people being frustrated running into its limitations as something to interact with creatively. I've tried a couple times to start game projects involving LLMs, and get the feeling that there is a lot of exploration that needs to be done into what can be done well and where that intersects with what is actually fun. Kind of don't expect EA to be the one to do that.

Just look at skate. Now imagine that but somehow worse and even uglier

Your experience counts for jack shit. There is zero evidence that AI is substantially improving efficiency. There is some that suggests its effect is negative.

They all went to the same Donald Trump business school. 1. Wages are very expensive. 2. Fire as many people as you can. 3. Shareholders see number go up.

EA is the world's shittiest game company. Just gutter trash all the way through.

This is not going to end well.

Last thing I bought from them was Mass Effect (only the first one) circa 2008 I think.

Sure, why not? Its up to gamers to dump them, and only time will tell how this will evolve. It also comes to the point replacing employees with AI.

Just so people know, you can ignore games by publisher in steam by searching their name in the store, clicking their page, then click the gear icon to ignore. EA who? Ubiwhat?

For those that don't know, Stability AI is already a zombie, even in the local ML community. SD3 was a flop, and they shed all their devs/projects worth anything.

I've had EA on ignore for *years* and they still showed up on my front page during the last sale !

I dream of AI being used to generate cool, theme appropriate NPCs for an indie dev that doesn't have an army of talented writers at their disposal. But honestly let's face it, that's never what they'll aim for. It's all about not paying people, for these assholes. They'll happily *fire* their talented writers of they can use AI instead, never once wondering who's gonna feed the AI in the first place. And so it is a matter of principle to say no to AI in general, because you know they'll always pick the worst possible way to use it.

Why punish valve? Do that shit through origin.

Ubishit.

I don't want to punish my computer by installing origin.

This is actually kind of interesting. This gamble is very likely to fail, EA could finally die, and its valuable IP sold off to companies that would actually make better use of them. The only wrinkle in this is that Trump's son in law owns EA now, so if it does end up failing, they'll probably find a way to get US tax payers to bail them out.

We are entering the dark ages of AAA games. They are going to be shallow ugly, buggy and dumb. Support indie devs.

And your comment also counts for jackshit since you provided no evidence of your claims, not even your own experience. So you can fuck right off, buddy.

You make the claim it has an order of magnitude benefit, then you get to provide the proof. And there isn't any. [There is some evidence that people will fool themselves into thinking it makes them faster](https://www.reuters.com/business/ai-slows-down-some-experienced-software-developers-study-finds-2025-07-10/), and it sounds like you're one of them.

Clearly the fix the AAAA games.