Viewing all submissions from lesswrong.com

Six Dimensions of Operational Adequacy in AGI Projects — LessWrong (lesswrong.com)
·
·
10 months ago
· comment
venki / ai-safety ×
Shallow review of live agendas in alignment & safety — LessWrong (lesswrong.com)
·
·
10 months ago
· comment
venki / ai-safety ×
The Field of AI Alignment: A Postmortem, and What To Do About It — LessWrong (lesswrong.com)
·
·
10 months ago
· comment
venki / ai-safety ×
Ten Levels of AI Alignment Difficulty — LessWrong (lesswrong.com)
Great post to understand why different actors might have different takes on alignment-tractability
·
·
10 months ago
· comment
venki / ai-safety ×
On how various plans miss the hard bits of the alignment challenge — LessWrong (lesswrong.com)
From Nate Soares about why to be pessimistic about all technical alignment approaches
·
·
10 months ago
· comment
venki / ai-safety ×
(My understanding of) What Everyone in Technical Alignment is Doing and Why — LessWrong (lesswrong.com)
·
·
10 months ago
· comment
venki / ai-safety ×