The developer behind Teach My Little Sister How to Drive, a driving instruction sim where you instruct a generative-AI-powered, dynamic NPC, has been spending $1,000 dollars a day to keep the demo working.

all 28 comments

sorted by: hot top controversial new old
[–] 111 points 1 month ago (4 children)

Teach My Little Sister How to Drive relies on Google Gemini and ChatGPT to power its dynamic NPC, which follows your instructions, reacts, and disobeys, but the developers are looking into ways of allowing local AI models to step in for players “with sufficiently capable PCs.”

They're using two cloud-based models for a task that is usually handled by if-then-else statements? I think I know who programmed this NPC...

  • source
  • hideshow 4 child comments
  • [–] 56 points 1 month ago* (1 child)

    Why use an if statement that compiles down to a conditional branch instruction and takes a nanosecond or two to execute, when you can outsource the decision making to a paid cloud service with expensive hardware that multiplies matrices with billions of elements to get your answer?

  • source
  • parent
  • hideshow 1 child comment
  • [–] 6 points 1 month ago* (last edited 1 month ago)

    This past week at work we had a server that kept getting overloaded because the customer started heavily using a feature that directly runs multiple files from the command line for each interaction. The feature was built long before I was there, and not thought out very well. Each files loads the same dependencies every time it's run which takes ~5 seconds under heavily load x 50 scripts trying to run at the same time.

    I pointed this out for the 3rd time that day while my coworker who has seniority was trying to figure out thy the server was stalling and kept just deploying updates that chatgpt suggested. Suggested to turn those scripts into reusable modules so we load the dependencies once and fork them to run in the background, but the coworkers robot said forking would actually be more resource intensive than running the scripts, which isn't true if you think about it for half a second.

    In the end, he said "Astra says we should upgrade the instance to and avoid updated the legacy script since they're working as is". My boss finally chimed in when he realized the coworker upgraded the instance from one that cost ~$200/m to one that would have cost ~$2,000 with like 60 cores and a gpu for some reason. His excuse was the robot suggested it and he stood by that decision.

    Thanks for listening to me rant.

  • source
  • parent
  • [–] 41 points 1 month ago* (3 children)

    When will people learn that cloud (aka someone else's computer you rent) is not a good deal for this sort of task? A person smart enough to write a game should really have the fore-thought to estimate the costs up-front of using an external service as part of it.

    On the other hand, I'm happy if people token-max the FREE tiers of "AI", to drive these a-hole companies out of business faster. It's just unsustainable and the big cloud companies are burning money way faster than they can realistically charge for it, so the more free 'burners' going, the better, in a twisted way. Bankrupt those MFers, no mercy.

  • source
  • hideshow 3 child comments
  • [–] 11 points 1 month ago

    A person smart enough to write a game

    It's really not hard to write a game these days. (Good or high end games are a different story). These pictures look 100% asset flipped using a driving sim tutorial project. There is zero smarts required. I'd be surprised if they didn't just download a demo project and plug in the LLM.

  • source
  • parent
  • [–] 32 points 1 month ago (2 children)

    The game is also popular in Asia, where there isn’t such a stigma around generative AI, which people in the West tend to hate because it’s a theft engine that sucks up the planet’s energy like Shinra.

  • source
  • hideshow 2 child comments
  • [–] 26 points 1 month ago* (last edited 1 month ago) (3 children)

    I did not realize that this game was backing the little sister character with a live cloud-based LLM. I just assumed it was something that would be a pre-trained local thing, or just have a finite set of responses.

    That seems horrifically unsustainable.

  • source
  • hideshow 3 child comments
  • [–] 1 point 1 month ago (1 child)

    In theory it's less complicated to handle a local AI with local resources. Remote AI would have been far more complex before the current state of AI. This method is just lazey API plugins that probably are asking the same prompts repeatedly. It looks to me to be a game trying to wedge LLMs into the industry. Has there been any effort to reduse the token burn or is it too fundamental to the game?

  • source
  • parent
  • hideshow 1 child comment
  • [–] 2 points 1 month ago

    from the article it sounds like the devs are looking into ways of integrating local AI, but for now its just prompting ChatGPT and Gemini for responses for the little sister character. Basically, the gameplay is you tell the NPC what to do with your microphone, she seems to pause for a sec, then reacts by saying something and maybe carrying out whatever it is you told her to do.

    Like you could say "Turn the wheel 50% left and accelerate to 20 km/h" and she would respond. From the gameplay i've seen, it seems pretty hit or miss if she reacts correctly. Like I watched a few 2ish hour streams of it and it pretty much took that long to get through the 3 or 4 levels in the demo, and most of that was the NPC not really responding in a consistent way. Basically, the AI reliance seems entirely central to the gameplay loop at this point.

  • source
  • parent
  • [–] 23 points 1 month ago (1 child)

    Sounds like a perfect microcosm of the whole stupid thing. It's basically the "SliceLine" business model, from Silicon Valley. (Where they were buying Dominos' pizzas and putting them in their own boxes and reselling them for less than a Domino's pizza.) You can't make a profit, can't even not lose money with every customer. But you can burn venture capital to offer your product at a loss and then use your increasing revenue to attract more investor money, while promising a new version of the service that actually will be profitable, right around the corner, real soon now- and hope to get bought out before your bullshit all falls apart.

  • source
  • hideshow 1 child comment
  • [–] 15 points 1 month ago (1 child)

    Then the bank was foolish to approve the loan.

  • source
  • hideshow 1 child comment
  • [–] 10 points 1 month ago

    Well, they’re an idiot then. Smh

  • source
  • [–] 9 points 1 month ago

    Well now I want to play this just so I can burn up more of this guys money and then never buy the thing since it seems extremely limited.

  • source
  • [–] 4 points 1 month ago

    I've seen a YouTuber or two playing this game. It looked like shit. And knowing that it needed too large language models just to play so poorly. Confirms that it's shit.

  • source
  • [–] -2 points 1 month ago (4 children)

    NPCs in games may be one of the very few actual good uses for AI. But not using the cloud obviously.

  • source
  • hideshow 4 child comments
  • [–] 2 points 1 month ago*

    Theoretically.

    In practice, 95% of consumer GPUs are too busy and too small to run an LLM good enough for dialogue, or a decision model smart enough to be warranted over hardcoded logic.

    CPUs are too slow. NPUs aren’t universal and are, unfortunately, all but useless with modern software frameworks.

    I am very much for LLM NPCs; there are some fantastic mods for such things.

    But in shipping games? That can’t be jank?

    It is not time. And I would never buy a game with a hard cloud dependency for SP. We will have to get past the RAMpocalypse, at the very least.

  • source
  • parent
  • 74 comments in c/games@lemmy.world view that post