"The Waluigi Effect (mega-post)" by Cleo Nardo

https://www.lesswrong.com/posts/D7PumeYTDPfBTp3i7/the-waluigi-effect-mega-post

In this article, I will present a mechanistic explanation of the Waluigi Effect and other bizarre "semiotic" phenomena which arise within large language models such as GPT-3/3.5/4 and their variants (ChatGPT, Sydney, etc). This article will be folklorish to some readers, and profoundly novel to others.