Explaining OCD to AI bros: mech interp your own reasoning traces

ChrisGPT · x · 2026-10-19

A viral AI-circle joke from ChrisGPT: the best way to explain OCD to an "AI bro" is that we feel the dire necessity to mech interp our own reasoning traces, or our polysemantic neurons start screaming — mapping interpretability research jargon onto intrusive mental loops.

Original post →

More from Fun

Fun channel →