AI ALIGNMENT FORUM
Tags
AF

Distillation & Pedagogy

•

Applied to An Illustrated Summary of "Robust Agents Learn Causal World Model" by Dalcy 7d ago

•

Applied to Concrete Methods for Heuristic Estimation on Neural Networks by Oliver Daniels 1mo ago

•

Applied to Graceful Degradation by Screwtape 2mo ago

•

Applied to Distillation Of DeepSeek-Prover V1.5 by IvanLin 2mo ago

•

Applied to Podcast: "How the Smart Money teaches trading with Ricki Heicklen" (Patrick McKenzie interviewing) by Raymond Arnold 5mo ago

•

Applied to Video Intro to Guaranteed Safe AI by Mike Vaiana 5mo ago

•

Applied to DIY RLHF: A simple implementation for hands on experience by Mike Vaiana 5mo ago

•

Applied to Poker is a bad game for teaching epistemics. Figgie is a better one. by RobertM 5mo ago

•

Applied to Dialogue introduction to Singular Learning Theory by Olli Järviniemi 5mo ago

•

Applied to An Extremely Opinionated Annotated List of My Favourite Mechanistic Interpretability Papers v2 by Neel Nanda 5mo ago

•

Applied to How ARENA course material gets made by CallumMcDougall 6mo ago

•

Applied to Distillation of 'Do language models plan for future tokens' by TheManxLoiner 6mo ago

•

Applied to Failure Modes of Teaching AI Safety by Eleni Angelou 6mo ago

•

Applied to AI Safety Strategies Landscape by Charbel-Raphael Segerie 7mo ago

•

Applied to Observations on Teaching for Four Weeks by ClareChiaraVincent 8mo ago

•

Applied to Ironing Out the Squiggles by Lauren (often wrong) 8mo ago

•

Applied to Superposition is not "just" neuron polysemanticity by Lawrence Chan 8mo ago

•

Applied to "Deep Learning" Is Function Approximation by Lauren (often wrong) 9mo ago