AI ALIGNMENT FORUMTags
AF

Distillation & Pedagogy

•

Applied to AI Safety Strategies Landscape by Charbel-Raphael Segerie 5d ago

•

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

•

Applied to Ironing Out the Squiggles by Lauren (often wrong) 14d ago

•

Applied to Superposition is not "just" neuron polysemanticity by Lawrence Chan 19d ago

•

Applied to "Deep Learning" Is Function Approximation by Lauren (often wrong) 2mo ago

•

Applied to AI Safety 101 : Capabilities - Human Level AI, What? How? and When? by markovial 2mo ago

•

Applied to Getting rational now or later: navigating procrastination and time-inconsistent preferences for new rationalists by RobertM 3mo ago

•

Applied to CFAR Takeaways: Andrew Critch by Raymond Arnold 3mo ago

•

Applied to Explaining Impact Markets by Tobias D. 3mo ago

•

Applied to Uncertainty in all its flavours by Cleo Nardo 4mo ago

•

Applied to A Pedagogical Guide to Corrigibility by A.H. 4mo ago

•

Applied to Learning Math in Time for Alignment by Nicholas Kross 4mo ago

•

Applied to Results from the Turing Seminar hackathon by Charbel-Raphael Segerie 5mo ago

•

Applied to The 101 Space You Will Always Have With You by RobertM 5mo ago

•

Applied to How I got so excited about HowTruthful by Bruce Lewis 6mo ago

•

Applied to Learning-theoretic agenda reading list by Raymond Arnold 6mo ago

•

Applied to AI Safety 101 : Reward Misspecification by markovial 7mo ago

•

Applied to A thought experiment to help persuade skeptics that power-seeking AI is plausible by jacobcd52 7mo ago

•

Applied to Join AISafety.info's Distillation Hackathon (Oct 6-9th) by RobertM 7mo ago