This would be an awesome feature to have. However, it’ll be very hardware and software dependent. The device needs to wake up constantly to poll if there’s a new demo or game to download.

This is surprisingly a hard problem to solve due to underlying bugs in the embedded firmware and the OS.

Much appreciated <3

Do you have a good resource for how one can go about this?

I would not recommend LocalAI. There documentation is somewhat lacking and it’s an all in one utility with many moving parts. The parts also tend to break, quite often.

deleted by creator

I am currently migrating away from my 6th gen i5 to a newer N100.

Speed wise, it was about the same as the coral, about 6-8ms on the i5.

I have a similar setup and it’s been a huge pain when I when I have to do the OS updates.

The Coral needs a dkms module, but the sources and Google’s own documentation for it are out of date. I would highly recommend using the iGPU for inference.

That’s quite punny if you asked me.

This is not due to the 13/14th generation CPU recall, rather Intel as a whole is floundering.

They missed the entire AI gravy train, losing market share to AMD, lost Apples business, etcetera. Intels foundry requires a lot of capital for both RnD and to keep the fabs running. They are losing market share and they have higher cost business compared to their competitors.

Funnily enough, the Onexfly F1 Pro just went up for sale too. The newer “AI HX” chips are expensive because where top end sku for Onexfly costs $1399.

I suspect that Ayaneo 3 will also have similar pricing.

I am pretty sure 2.5GBe will work over normal/standard CAT5 and Cat5e cable. It’s the upstream switch that you’ll need to replace.

Quick shout out to yt-dlp. It comes everything you need to download, transcode, and even use Sponsorblock!