MHLoppy

I don't know how well this works for Macs, but is a multi-boot environment a possibility? You could have a separate OS set up for a group of tasks which you boot into when you need to do that. It seems a bit clunky compared to e.g., virtual desktops or similar though.

So they literally agree not using an LLM would increase your framerate.

Well, yes, but the point is that at the time that you're using the tool you don't need your frame rate maxed out anyway (the alternative would probably be alt-tabbing, where again you wouldn't need your frame rate maxed out), so that downside seems kind of moot.

Also what would the machine know that the Internet couldn‘t answer as or more quickly while using fewer resources anyway?

If you include the user's time as a resource, it sounds like it could potentially do a pretty good job of explaining, surfacing, and modifying game and system settings, particularly to less technical users.

For how well it works in practice, we'll have to test it ourselves / wait for independent reviews.

It sounds like it only needs to consume resources (at least significant resources, I guess) when answering a query, which will already be happening when you're in a relatively "idle" situation in the game since you'll have to stop to provide the query anyway. It's also a Llama-based SLM (S = "small"), not an LLM for whatever that's worth:

Under the hood, G-Assist now uses a Llama-based Instruct model with 8 billion parameters, packing language understanding into a tiny fraction of the size of today’s large scale AI models. This allows G-Assist to run locally on GeForce RTX hardware. And with the rapid pace of SLM research, these compact models are becoming more capable and efficient every few months.

When G-Assist is prompted for help by pressing Alt+G — say, to optimize graphics settings or check GPU temperatures— your GeForce RTX GPU briefly allocates a portion of its horsepower to AI inference. If you’re simultaneously gaming or running another GPU-heavy application, a short dip in render rate or inference completion speed may occur during those few seconds. Once G-Assist finishes its task, the GPU returns to delivering full performance to the game or app. (emphasis added)

It's technically an option, yeah, but as you said it's not something practically used as an "everyday" feed-sorting algorithm. It's not as though it's a default or suggested sort option - compare that to Mastodon where it's the only sort option X_X

Definitely agree that the the common-with-Mastodon viewpoint of exclusively using chronological feeds seems to have over-corrected too far. Can you imagine if the threadiverse was sorted that way? It would be insane and essentially unusable at scale - so we can at least acknowledge that sorting algorithms have a useful place and are not some unsalvageable, irredeemable evil. I wish there was something like a bunch of open source algorithms which the user could choose between in whatever UI they're using. At the very least there should be some acknowledgement that I, the user, don't have an identical level of interest in every account I follow, or even in every topic which the same account posts about.

And while microblogging platforms seem to have it worst, there have also been times in the threadiverse where I've subscribed to a community/magazine only to later unsubscribe because the activity levels it produces in my feed are much higher than my interest levels in it. So even here (where we have sorting by "hot" etc), some kind of user-configurable weighting would be nice to better match how I actually want my feed to work!

edit: typo

Would be curious to read the LLM output.

It looks like it's available in the linked study's paper (near the end)

What a dumbass, commenting lemmy.zip but from a feddit.org account /s

For what it's worth I generally agree with you, and especially think the people who treat /all as their own personal feed are nuts, but nonetheless it's something that some people do 🫠

Everyone has their own preferences about how to use things!

Browsing the global/all feed is one way to find new communities, and some people just like using it in general rather than defaulting to a subs-only view.

Just be aware that some places/connections have trouble connecting with it: https://catbox.moe/faq.php (under Connectivity Issues)

Crazy that this is how I found out about this. I guess that's what I get for not being enough of a repost bot 😔