Research JournalsShoshannah TekofskySep 22, 2022, 7:20 PMWeekly notes, musings, ideas, and insights from my 6 month journey skilling up in AI Safety.Research Principles for 6 Months of AI Alignment StudiesShoshannah TekofskyDec 2, 2022, 10:55 PM23 points3 comments6 min readLW linkThree Alignment Schemas & Their ProblemsShoshannah TekofskyNov 26, 2022, 4:25 AM19 points1 comment6 min readLW linkLoose Threads on IntelligenceShoshannah TekofskyDec 24, 2022, 12:38 AM11 points3 comments8 min readLW linkOptimizing Human Collective Intelligence to Align AIShoshannah TekofskyJan 7, 2023, 1:21 AM12 points5 comments6 min readLW linkReflections on Deception & Generality in Scalable Oversight (Another OpenAI Alignment Review)Shoshannah TekofskyJan 28, 2023, 5:26 AM53 points7 comments7 min readLW linkA Simple Alignment TypologyShoshannah TekofskyJan 28, 2023, 5:26 AM34 points2 comments2 min readLW linkShort Notes on Research ProcessShoshannah TekofskyFeb 22, 2023, 11:41 PM21 points0 comments2 min readLW link