Marijuana, on the other hand, has almost always made me temporarily psychotic, or at least paranoid. It's also very safe physically. I'd be curious to know about any decent rationalists' attempts to "beat" this or other drugs.

I've used bayesianism to stop myself from being paranoid after smoking marijuana. I don't get it too badly, but I tend to think random events are related to me, eg that police car driving down the street with it's sirens on is coming for me, or the runner in the park is here to mug me. Besides being able to understand that I'll deliberately altered my mental state and can make reference to how I would feel in an unaltered state, I've also taken a moment to pause and say something along the lines of "OK, given that it's highly implausible that the police know I'm high, I have a fairly low prior for 'random police car is coming for me'. Do I have any evidence that would have caused me to update my beliefs? No. So no reason to believe them". It works pretty well, but marijuana is a pretty soft drug imho. In my limited experience it's harder to reason yourself out of adverse mental states that can come from psilocybin a (sufficient quantities of) LSD