"The Waluigi Effect (mega-post)" by Cleo Nardo
LessWrong (Curated & Popular)
Chapters
0:32
Background
0:56
Prompting LLMs with direct queries
3:40
Prompting LLMs with flattery and dialogue
5:05
Simulator Theory
9:03
The limits of flattery
12:16
Derrida — il n'y a pas de hors-texte
15:17
The Waluigi Effect
17:00
(1) Rules are meant to be broken.
19:45
(2) Traits are complex, valences are simple.
22:03
(3) Structuralist narratology
25:42
Superpositions will typically collapse to waluigis
27:48
Evidence from Microsoft Sydney
28:42
Waluigis after RLHF
31:19
(2) Empirical evidence from Perez et al.
33:11
(3) RLHF promotes mode-collapse
40:22
Conclusion
LessWrong (Curated & Popular)
"The Waluigi Effect (mega-post)" by Cleo Nardo
Mar 08, 2023
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.
