LESSWRONG
LW

1996
Research Journals

Research Journals

Sep 22, 2022 by Shoshannah Tekofsky

Weekly notes, musings, ideas, and insights from my 6 month journey skilling up in AI Safety.

23Research Principles for 6 Months of AI Alignment Studies
Shoshannah Tekofsky
3y
3
19Three Alignment Schemas & Their Problems
Shoshannah Tekofsky
3y
1
11Loose Threads on Intelligence
Shoshannah Tekofsky
3y
3
12Optimizing Human Collective Intelligence to Align AI
Shoshannah Tekofsky
3y
5
53Reflections on Deception & Generality in Scalable Oversight (Another OpenAI Alignment Review)
Shoshannah Tekofsky
3y
7
34A Simple Alignment Typology
Shoshannah Tekofsky
3y
2
21Short Notes on Research Process
Shoshannah Tekofsky
3y
0