Hacker News Reader

The fundamental problem is that a subtle enough cheater is indistinguishable from a good enough human player.

Has been used for some time now.

https://x.com/deteccphilippe/status/1883945555102957617

> “Behavior” refers to an ML suspension (also called “server-sided” anti-cheat), often given to ragehackers.

But then you can just teach an AI to act like a human. Anti cheats in computer games is and always will be a cat and mouse game and AI/ML is just another tool in the bag of many tools (most bans seem to be fingerprinting based basically rebanning previous offenders who failed to get around the fingerprinting system)

Yes, that's the real solution, not rootkits.

AI certainly is not the solution. It has its issues, false positives, and there's barely any way to get support for that case as support agents are instructed with the AI being infallible.