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

LessWrong (Curated & Popular)
08/03/2023 41 min
"The Waluigi Effect (mega-post)" by Cleo Nardo

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

Descargar episodio

Episode Synopsis

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

More episodes of the podcast LessWrong (Curated & Popular)

"How AI Is Learning to Think in Secret" by Nicholas Andresen 08/01/2026
"On Owning Galaxies" by Simon Lermen 08/01/2026
"AI Futures Timelines and Takeoff Model: Dec 2025 Update" by elifland, bhalstead, Alex Kastner, Daniel Kokotajlo 06/01/2026
"In My Misanthropy Era" by jenn 05/01/2026
"2025 in AI predictions" by jessicata 02/01/2026
"Good if make prior after data instead of before" by dynomight 27/12/2025
"Measuring no CoT math time horizon (single forward pass)" by ryan_greenblatt 27/12/2025
"Recent LLMs can use filler tokens or problem repeats to improve (no-CoT) math performance" by ryan_greenblatt 23/12/2025
"Turning 20 in the probable pre-apocalypse" by Parv Mahajan 23/12/2025
"Alignment Pretraining: AI Discourse Causes Self-Fulfilling (Mis)alignment" by Cam, Puria Radmard, Kyle O’Brien, David Africa, Samuel Ratnam, andyk 23/12/2025
© 2003-2026 ZARZA | AHEAD OF OUR TIME
privacy policy
In God we trust In God we trust
PreSales Questions? Click Here
or call our toll-free line at +1-888-5002068 Miami, Florida, USA