This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
Research Journals
LW
Login
Research Journals
Weekly notes, musings, ideas, and insights from my 6 month journey skilling up in AI Safety.
22
Research Principles for 6 Months of AI Alignment Studies
Shoshannah Tekofsky
6mo
3
19
Three Alignment Schemas & Their Problems
Shoshannah Tekofsky
7mo
1
11
Loose Threads on Intelligence
Shoshannah Tekofsky
6mo
3
14
Optimizing Human Collective Intelligence to Align AI
Shoshannah Tekofsky
5mo
4
53
Reflections on Deception & Generality in Scalable Oversight (Another OpenAI Alignment Review)
Shoshannah Tekofsky
5mo
6
34
A Simple Alignment Typology
Shoshannah Tekofsky
5mo
2
21
Short Notes on Research Process
Shoshannah Tekofsky
4mo
0