Research JournalsShoshannah Tekofsky22 Sep 2022 19:20 UTCWeekly notes, musings, ideas, and insights from my 6 month journey skilling up in AI Safety.Research Principles for 6 Months of AI Alignment StudiesShoshannah Tekofsky2 Dec 2022 22:55 UTC23 points3 comments6 min readLW linkThree Alignment Schemas & Their ProblemsShoshannah Tekofsky26 Nov 2022 4:25 UTC19 points1 comment6 min readLW linkLoose Threads on IntelligenceShoshannah Tekofsky24 Dec 2022 0:38 UTC11 points3 comments8 min readLW linkOptimizing Human Collective Intelligence to Align AIShoshannah Tekofsky7 Jan 2023 1:21 UTC12 points5 comments6 min readLW linkReflections on Deception & Generality in Scalable Oversight (Another OpenAI Alignment Review)Shoshannah Tekofsky28 Jan 2023 5:26 UTC53 points7 comments7 min readLW linkA Simple Alignment TypologyShoshannah Tekofsky28 Jan 2023 5:26 UTC34 points2 comments2 min readLW linkShort Notes on Research ProcessShoshannah Tekofsky22 Feb 2023 23:41 UTC21 points0 comments2 min readLW link