LESSWRONGTags
LW

Distillation & Pedagogy

•

Applied to AGISF 2022 Summaries by Ishan at 14d

•

Applied to The AI Control Problem in a wider intellectual context by philosophybear at 17d

•

Applied to Induction heads - illustrated by Ruby at 1mo

•

Applied to Models Don't "Get Reward" by DragonGod at 1mo

•

Applied to Summary of 80k's AI problem profile by Ruby at 1mo

•

Applied to Shard Theory in Nine Theses: a Distillation and Critical Appraisal by LawrenceC at 1mo

•

Applied to MIRI's "Death with Dignity", but in 80 seconds. by Cleo Nardo at 2mo

•

Applied to The No Free Lunch theorem for dummies by Steven Byrnes at 2mo

•

Applied to Distillation of "How Likely Is Deceptive Alignment?" by Noosphere89 at 2mo

•

Applied to I Converted Book I of The Sequences Into A Zoomer-Readable Format by Raemon at 3mo

•

Applied to Distillation Experiment: Chunk-Knitting by Raemon at 3mo

•

Applied to Real-Time Research Recording: Can a Transformer Re-Derive Positional Info? by Neel Nanda at 3mo

•

Applied to Power-Seeking AI and Existential Risk by Ruby at 4mo

•

Applied to Understanding Infra-Bayesianism: A Beginner-Friendly Video Series by Jack Parker at 4mo

•

Applied to Summaries: Alignment Fundamentals Curriculum by Ruby at 4mo

•

Applied to Deep Q-Networks Explained by Jay Bailey at 5mo

•

Applied to How To Know What the AI Knows - An ELK Distillation by Ruby at 5mo

•

Applied to Alignment is hard. Communicating that, might be harder by Raemon at 5mo

•

Applied to AI alignment as “navigating the space of intelligent behaviour” by Nora_Ammann at 5mo

•

Applied to Epistemic Artefacts of (conceptual) AI alignment research by Nora_Ammann at 5mo