I keep my copilot subscription intact because it’s nice having access to remote LLMs at times, especially when debugging issues around my local setup. Otherwise I’ve been able to offload nearly everything to my local models.

I’ve been using Strata with Qwen 3.8 Flash Next and have been pretty happy with the results

I used the github copilot tui (since that was what my subscription was through) and told it what the devices were and what I was trying to accomplish. From there it was a mixture of different things to figure out how the protocols worked, like running the apps in wine and having it log and capture data as I changed settings, or have it flip bits and I would report to it what changed. If it discovers a component in the device is something off-the-shelf, have it find reference material from the component manufacturer.

As you figure out how a particular protocol works you have it document it until you have everything you need to build your own CLI to interface with the device. At that point you have a pretty good idea of how the device works and it’s capabilities and you can build out whatever features you want around it.

Oh I do pay for a subscription, just blew through my budget.

I have since moved to using mainly local models for everything. Running AI was why I was doing this PC build in the first place, just didn’t have it fully configured and I am wildly impatient when I get new stuff lol

I recently upgraded my PC and bought a case with a segmented display. Required a windows driver to work. I also bought a CPU liquid cooler with a display on it. Also required a windows app.

I threw about 30 bucks in tokens and now I have linux ports for both and with every added every feature I could come up with.

Now any weird or obscure piece of hardware I have that has been defunct for lack of software support has been getting the same treatment.

Resource management comes in many different flavors. Most computers allow you to use every resource it has at its disposal to accomplish a task (rendering graphics, processing workloads, gaming, etc), and that would really suck to have your system just decide it should nuke that process. It doesn’t really know what you prioritize, so Instead it runs and compromises the best it can until the dam breaks. But gaming is a little less of a gray area, its nearly always the main focus of the user, so its easy to draw a line there.

There are systems that are far more opinionated about resource usage that will reign in processes. Like iOS is a good example (The divide is usually desktop and mobile OSs). It prioritizes UI, battery life, and animation fluidity over any process and will kill anything that threatens it.

There are applications out there you can use to limit resource usage per app, so you can limit the resources of bloated browser engines that masquerade as native apps.