> Automation has “tells” - little things they do differently from what humans would do

This tends to stand out like a sore thumb once you start looking at things from the perspective of the frequency domain. Even if you use an RNG to delay activity, the properties of the RNG itself can be leveraged against it. You may think taping a pencil to a desk fan and having that click the mouse button is being clever wrt undetectable RNG, but you must realize that the power grid runs at 50/60hz and induction motors are ~fixed to this frequency.

There is also the entire space of correlation. A bot running on random pixel events with perfectly human response times, while appearing "random", is not correlated with anything meaningful outside that one pixel being monitored. You could check for what are effectively [near] causality violations to determine the probability that the player is actually human.

But... humans kinda behave the same? Your FPS is 50/60 Hz and your reactions are pretty much tied to it; and human behaviour is a pretty lousy RNG, that's been known for ages.

> A bot running on random pixel events with perfectly human response times, while appearing "random", is not correlated with anything meaningful outside that one pixel being monitored

So would a human who is tunneled-vision at the center of the screen.

What if one were to train a neural network of sorts based on your response times and mouse paths toward on screen stimuli?

I’ve thought that trying to make a bot for personal fishing use would be a delightfully fun project, and this is how I pondered evading such anti-cheat heuristics.