Well that can be said for every product ever...
I do agree though, I did expect a little more real content. Not the "how anti-cheat works" because then we can find ways around it more easily, but like you said: reliability, performance, etc.
In general, this type of human/AI side-by-side feedback loop seems to be very successful, all the way from games to moderating content on the web.
especially with how opaque the whole flagging is.
I understand why they do it and a game environment is not a democracy or a court of law, but it's hard to defend yourself when you do not have access to the evidences.
The oft-used 'arms race' analogy for this would be like sending blueprints of your newly-fabricated weapons to the adversary.
The fact is 99 out of 100 banned users were actually banned for good reason and are lying about not cheating. Half of those will also dmit to cheating but beg for forgiveness as if they aren't quite literally destroying the game and everyone's enjoyment of it. That less than 1 percent that is truly innocent is nearly impossible to service because of all the noise.
Long ago I was using a custom Linux box with a slow GPU, and on one map no matter how hard I tried (and no matter how many fellow players watched trying to help me get the timing right) I simply couldn’t jump to the first level of a building.
I’d never experienced a hardware limitation quite like that.
I think the article missed an opportunity to talk about false positive rates, the workflow for users to get unbanned due to false positives (usually a very nasty process), performance, platform support (Windows, for example, has encrypted app packaging [1], anti-cheat monitoring [2], and protected processes [3] built in), and the privacy implications of uploading non-game-related Windows driver and process data.
[1] https://docs.microsoft.com/en-us/windows/uwp/packaging/creat...
[2,3] https://docs.microsoft.com/en-us/windows/uwp/packaging/app-c...