LESSWRONGResearch Journals
LW

Research Journals

Sep 22, 2022 by Shoshannah Tekofsky

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

22Research Principles for 6 Months of AI Alignment Studies
Shoshannah Tekofsky
4mo
3
16Three Alignment Schemas & Their Problems
Shoshannah Tekofsky
4mo
1
11Loose Threads on Intelligence
Shoshannah Tekofsky
3mo
3
14Optimizing Human Collective Intelligence to Align AI
Shoshannah Tekofsky
3mo
4
52Reflections on Deception & Generality in Scalable Oversight (Another OpenAI Alignment Review)
Shoshannah Tekofsky
2mo
6
34A Simple Alignment Typology
Shoshannah Tekofsky
2mo
2
21Short Notes on Research Process
Shoshannah Tekofsky
1mo
0