Sveriges mest populära poddar
LessWrong (Curated & Popular)
Samhälle och kulturTeknologi

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

41 min•8 mars 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.

Fler avsnitt av LessWrong (Curated & Popular)

Visa alla avsnitt av LessWrong (Curated & Popular)
"What is up with e/acc?" by KatjaGrace
•4 min
"Existential AI safety needs an effective social movement. PauseAI is building it" by Maxime Fournes, Espedair Street
•1 tim 3 min
"Surprising facts about the slave trade" by Joseph Miller
•13 min
"AI catastrophe: more like a genocide than a thought experiment" by KatjaGrace
•2 min
"AI pause: the case for ASAP" by KatjaGrace
•2 min
"The Invisible Side of AI Governance" by Charbel-Raphaël
•28 min
"A Theory of Prompt Injection (and why you should study roles)" by Charles Ye, softboiledheart
•32 min
"Machinic Psychopharmacology: Do LLMs Self-Medicate?" by Sid Black, Joseph Bloom
•53 min
"Can activation verbalizers surface an internal chain of thought?" by oakhu, ryan_greenblatt
•1 tim 20 min
"The LLM shoggoth meme is weirder than you think" by HedonicEscalator
•14 min

LessWrong (Curated & Popular) med LessWrong finns tillgänglig på flera plattformar. Informationen på denna sida kommer från offentliga podd-flöden.