x
This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
LW
Login
Research Journals — LessWrong
Research Journals
Weekly notes, musings, ideas, and insights from my 6 month journey skilling up in AI Safety.
23
Research Principles for 6 Months of AI Alignment Studies
Shoshannah Tekofsky
3y
3
19
Three Alignment Schemas & Their Problems
Shoshannah Tekofsky
3y
1
11
Loose Threads on Intelligence
Shoshannah Tekofsky
3y
3
12
Optimizing Human Collective Intelligence to Align AI
Shoshannah Tekofsky
3y
5
53
Reflections on Deception & Generality in Scalable Oversight (Another OpenAI Alignment Review)
Shoshannah Tekofsky
3y
7
34
A Simple Alignment Typology
Shoshannah Tekofsky
3y
2
21
Short Notes on Research Process
Shoshannah Tekofsky
3y
0