A Moderate Update to your Artificial Priors — LessWrong
LESSWRONG BOOKS OF LESSWRONG LOGIN A Moderate Update to your Artificial Priors Jan 03, 2024 by habryka 231 ARC's first technical report: Eliciting Latent KnowledgeΩ paulfchristiano, Mark Xu, Ajeya Cotra 5y 90 232 Fun with +12 OOMs of ComputeΩ Daniel Kokotajlo 5y 86 633 What 2026 looks likeΩ Daniel Kokotajlo 5y 174 266 Ngo and Yudkowsky on alignment difficultyΩ Eliezer Yudkowsky, Richard_Ngo 5y 153 254 Another (outer) alignment failure storyΩ paulfchristiano 5y 39 300 What Multipolar Failure Looks Like, and Robust Agent-Agnostic Processes (RAAPs)Ω Andrew_Critch 5y 65 265 The PlanΩ johnswentworth 5y 78 157 Finite Factored SetsΩ Scott Garrabrant 5y 97 136 Selection Theorems: A Program For Understanding AgentsΩ johnswentworth 5y 29 162 My research methodologyΩ paulfchristiano 5y 38 261 larger language models may disappoint you [or, an eternally unfinished draft]Ω nostalgebraist 5y 31 139 Comments on Carlsmith's “Is power-seeking AI an existential risk?”Ω So8res 5y 15 307 EfficientZero: How