SteamOS as a whole is not open source. Most of it is, but it also includes proprietary software (e.g. Steam itself). This is likely why you were downvoted, as SteamOS can be kept private without violating any license thus your first statement was false.

Valve could distribute each single piece of open source software they use on request to their customers, without publishing any guide to actually build it. (Thanks for linking to Valve’s repo, which seems to match this statement.)

This is how Apple does it with Darwin, the BSD-derived open source core of macOS. Without all the proprietary parts it’s not useful as an OS, even though they follow all the necessary licensing.

I’ve just looked it up and the A380 seems to only draw ~17W at idle. That’s better than I thought, but still 2-3 times a HDD.

I wonder whether the new generation will lower the idle power usage too, or only the performance per watt.

It likely depends on how much they pay for power and how many users they serve.

E.g. I’d really like AV1 support on my server (helps with slow upload), but the cost for power of a dedicated GPU is inacceptable in my country. The few transcoding reams I’d theoretically need in a worst case scenario are more than met with an iGPU.

This proves that AC Oddysey runs faster on Linux than on Windows with your specific hardware. What this doesn’t mean is that “Linux gaming is faster and smoother than Windows gaming”.

Counter examples are Overwatch, CS:2, GTA V and many more.

Nobody reasonable doubts that Linux can perform as good or better than Windows, but claiming that this is true for all games is simply misinformation.

Wrong general claims like these lead to posts asking why their specific games run worse on Linux since they switched because they want more fps.

Don’t get me started on older GPU’s like 1000 series Nvidia that have problems with any vkd3d games so the performance is abysmal.

Why is it not enough that almost all games work on Linux with ±15% performance difference?