Mastodawn

Google's Gemini will make its way into Dragon Quest X to power a "Chatty Slimey" AI companion, Square Enix has announced

https://piefed.ca/c/games/p/614076/google-s-gemini-will-make-its-way-into-dragon-quest-x-to-power-a-chatty-slimey-ai-companion

Google's Gemini will make its way into Dragon Quest X to power a "Chatty Slimey" AI companion, Square Enix has announced

### Welcome 🍁 **Piefed.ca** is run by Canadians, hosted in Canada, and geared toward Canadians. However, it is not restricted to Canadians, or Canadian culture/topics/etc. All are welcome! To learn more about how the Fediverse works, you can visit our simple [Getting Started Guide](https://fedecan.ca/en/guide/get-started). This site is run by the non-profit [Fedecan](https://fedecan.ca/) and funded entirely by user donations. You can help support us by visiting our [donations page](https://fedecan.ca/en/donate). --- #### Rules and Guidelines ::: spoiler 1. No Bigotry Including racism, sexism, ableism, homophobia, transphobia, or xenophobia. ::: ::: spoiler 2. Be Civil Argue in good faith, attack the argument; not the person, and promote a healthy debate. That includes implying violence, threats or wishes of violence and/or death. ::: ::: spoiler 3. No Porn This instance is not made to host porn communities. You're free to access porn communities on other instances through your account, but be mindful of Rule 4. ::: ::: spoiler 4. Use the NSFW tag Use your common sense: if you wouldn't want this image to show up on your work computer, tag it as such. In comments, use the `:::spoiler :::` tag for NSFW images, and put a NSFW mention beside links. Do not use NSFW images as your avatar or banner. ::: ::: spoiler 5. No Ads / Spam This instance is not there to act as your billboard. If you want to promote your personal work, at least make the effort to be a contributing member of this community. Your account purpose shouldn't be to only advertise, make it natural. ::: ::: spoiler 6. Bot account If you are the operator of a "bot" account, make sure to flag is as such in the [account's settings](/settings). ::: ::: spoiler 7. Right to privacy Do NOT distribute the personal information of someone else without their consent (aka doxxing). Information that is public domain can be shared, provided it is in good faith. *ex: The official email of an elected official is fair, the private phone number or the real name of a non-public person is NOT.* ::: ::: spoiler 8. Report abuse The report function isn't labelled the *disagree* button. You might not agree with someone, but that doesn't mean what the person says is against the rules. Using it repeately in this fashion will lead to actions being taken against the reporter. ::: ::: spoiler 9. Impersonation Don't make an account with the intent to negatively deceive or defame someone on the fediverse. *ex: Parody of a famous person is okay, submitting outrageous content as appearing like another user, mod or admin isn't.* ::: --- **Contact an Admin:** - Send us a message at [@[email protected]](https://lemmy.ca/u/admin) - Send us an email at [[email protected]](mailto:[email protected]) **Guides:** You can find more guides at [fedecan.ca](https://fedecan.ca/en/guide/get-started) by opening the sidebar. - [Welcome to the Fediverse](https://fedecan.ca/en/guide/get-started) - [About Us (Fedecan)](https://fedecan.ca/en/guide/fedecan/) **Meta Communities:** - [!main](/c/[email protected]): announcements & general discussion **Site Status:** [status.fedecan.ca](https://status.fedecan.ca/) **Other Frontends:** Don't like how Lemmy looks? Try one of our [alternative UIs](https://fedecan.ca/en/guide/lemmy/for-users/alternative-uis): - [photon.piefed.ca](https://photon.piefed.ca/) (Photon) - [blorp.piefed.ca](https://blorp.piefed.ca/) (Blorp) --- **Find Apps:** [lemmyapps.com](https://www.lemmyapps.com/) **Find Communities:** [lemmyverse.net](https://lemmyverse.net/communities) **Fediseer:** [![endorsement](https://fediseer.com/api/v1/badges/endorsements/piefed.ca.svg)](https://gui.fediseer.com/instances/detail/piefed.ca)

Show thread

Pyro 3d ago

Honestly, a small llm in these situations would be great idea, but it should be a very small local or hosted by the company itself (with a setting to turn off)

A small AI in games is the stuff I do want. But there is no reason gemni needs to be involved in a game at all

Show thread

MyNameIsAtticus 3d ago

Make it a downloadable package that runs a local model and I think I’d be far more fine. Like, I think it’s a tacky gimmick, but at least on device it’s not hurting the environment

Show thread

Mirror Giraffe

I’m not too big on these topics and would like to understand. Is a local model less resource intensive?

In my mind, if every gamer runs a model that must be less efficient than a centralised one that has the perfect hardware setup and only lends out the resources needed for each slime or whatever.

I’m thinking that it of course would be better with a dedicated slime model than the entire Gemini monster but why is local better?

Show thread

MyNameIsAtticus 2d ago

Local runs on device, so no need to connect to a big data center that chugs lots of water and all those other problems. Of course, because it’s a smaller far tinier model it’s nowhere near as accurate, but especially for things like this you don’t really need a big accurate LLM model.

I think I also though I should warrant a disclaimer that I am a Software Developer, not a AI Developer. So there’s far less backing then from my perspective than someone who works with this stuff for a living

Show thread

Mirror Giraffe 2d ago

I’m also a sw engineer so we’re both guessing 😅

I’m guessing those dates centers use that water for cooling whereas most home computers run an electric fan. And furthermore they probably use less electricity per token as they want to maximize profits. I don’t have any numbers to back my hunch up but I’m pretty sure the environment would suffer more if everyone is running their own.

I probably missed a lot of factors such as what type of energy the centers run contra what average Joe runs etc.

Show thread

Cethin 2d ago

I don’t know, but I’m willing to bet that economies of scale actually mean data centers are more efficient. This isn’t to say their use is justified, just that they’re able to take advantage of things a home computer can’t.

However, having to run it locally means it needs to be much more limited. This is doubly true if you want to run the game and the LLM at the same time. The LLM is easily able to consume all resources your system has available if you allow it to, which means the game won’t run well (if it runs at all). This limits the use so it can’t just be shoved everywhere and constantly running, like it could if it’s sent to a data center. It’s not more efficient, just less consumption.

Show thread

SabinStargem 1d ago

On my system, I can play a RPG Maker game and use a 122b LLM at the same time, alongside to a podcast. A model in that parameter range takes up about 70gb of DDR4 RAM and 36gb of VRAM. However, it used to be that a 120b AI would take a larger footprint, bringing the system to the brink. The hardware requirements are going down, and the quality also increased, alongside speed. I believe when the next major sea change of hardware happens, AI will become very practical for gaming.

Show thread

Cethin 1d ago

Damn, your system is insane. Yeah, an RPG maker game is next to nothing compared to that. Still, Dragon Quest I think is 3D. It takes a lot more VRAM than RPG maker.

I have 16GB VRAM, which is a lot for most systems. That’s easily consumed by an LLM. Any model that doesn’t use at least that much tends to perform pretty poorly, in my experience. That’s not mentioning how much heat it generates while running, which has to be removed from the system or it’ll slow down. Even if your system can handle it, it heats up fast. It’s great when I need a heater running, but when I need AC my room gets warm quick.

Show thread

SabinStargem 1d ago

Keep in mind, a 122b (Qwen3.5 family), is high end for consumer machines, but it is likely that DQX would be using a much smaller model. Currently, we have Qwen models that are 8b, 9b, 27b, 35b, 122b, and 397b. Plus, ‘quanting’ can reduce how much memory a model takes up - at a tradeoff, o’course. I am guessing DQX would have multiple local models, and use the player’s hardware metrics to decide which model to deploy.

Alternatively, the Chatty Slime could rely on cloud AI. Depending on Square’s strategy, that could be a freebie or a paid service. If the Chatty Slime gave options to the player - say, trading a potion for a stat seed, or responding to a quiz, Square could sell player behavior data.

…Anyhow, my room has a mini-split AC. One of the best purchases in my life: my room lacked insulation in the first place, so it becomes toasty during summer. The side effect is being able to just run my GPU and not become a human slushy.

Show thread

Cethin 1d ago

Is your comment written by AI? It seems weird, and we already went over most of what it says.

Also, DQ runs on Nintendo systems. That makes me certain it’s cloud based.

Show thread

SabinStargem 1d ago

No, I didn’t use AI for that. Humans tend to come in many flavors.