AI ALIGNMENT FORUMTags
AF

Exercises / Problem-Sets

•

Applied to The Cognitive Bootcamp Agreement by Raymond Arnold 1mo ago

•

Applied to OODA your OODA Loop by Raymond Arnold 1mo ago

•

Applied to Forecasting One-Shot Games by Raymond Arnold 2mo ago

•

Applied to Brief notes on the Wikipedia game by Olli Järviniemi 4mo ago

•

Applied to Prompts for Big-Picture Planning by Raymond Arnold 7mo ago

•

Applied to Exercise: Planmaking, Surprise Anticipation, and "Baba is You" by Raymond Arnold 9mo ago

•

Applied to Meetup In a Box: Year In Review by Czynski 9mo ago

•

Applied to D&D.Sci(-fi): Colonizing the SuperHyperSphere by abstractapplic 10mo ago

•

Applied to Interpretability with Sparse Autoencoders (Colab exercises) by CallumMcDougall 1y ago

•

Applied to Staying Split: Sabatini and Social Justice by Alex Vermillion 1y ago

•

Applied to Game Theory without Argmax [Part 2] by Cleo Nardo 1y ago

•

Applied to Game Theory without Argmax [Part 1] by Cleo Nardo 1y ago

•

Applied to How well does your research adress the theory-practice gap? by Jonas Hallgren 1y ago

•

Applied to Impact stories for model internals: an exercise for interpretability researchers by Tassilo Neubauer 1y ago

•

Applied to Exercise: Solve "Thinking Physics" by Raymond Arnold 1y ago

•

Applied to Mech Interp Puzzle 2: Word2Vec Style Embeddings by Raymond Arnold 1y ago

•

Applied to Rationality !== Winning by Raymond Arnold 1y ago

•

Applied to Tiny Mech Interp Projects: Emergent Positional Embeddings of Words by Raymond Arnold 1y ago

•

Applied to Mech Interp Puzzle 1: Suspiciously Similar Embeddings in GPT-Neo by Raymond Arnold 1y ago

•

Applied to An Exercise to Build Intuitions on AGI Risk by Lauro Langosco 1y ago