LessWrong (Curated & Popular) cover image

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

LessWrong (Curated & Popular)

00:00

Introduction

This article will be folklorish to some readers and profoundly novel to others. The Waluigi Effect is a bizarre semiotic in quotes phenomena which arise within large language models such as GPT-3, 3.5 or 4. When LLMs first appeared, people realised that you could ask them queries. Recall that the internet doesn't just contain truths, it also contains common misconceptions, outdated information, lies, fiction, myths, jokes, memes, random strings, undeciphered logs, etc. And here we have Buster, the rabbit friend from the cartoon Hay Arthur looking concerned and confused. Back to the text.

Play episode from 00:00
Transcript

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app