LESSWRONGWei_Dai
LW

User Profile

25712Ω601033115

Recent Posts

Curated Posts
Curated - Recent, high quality posts selected by the LessWrong moderation team.
Learn More
Frontpage Posts
Posts meeting our frontpage guidelines: aim to explain, not to persuade. Avoid meta-discussion
(includes curated content and frontpage posts)
Learn More
All Posts
Includes personal and meta blogposts (as well as curated and frontpage).
Learn More

Three AI Safety Related Ideas

65
Wei_Dai
2d1 min readΩ 17Show Highlight
9

Counterintuitive Comparative Advantage

62
Wei_Dai
17d1 min readShow Highlight
6

Beyond Astronomical Waste

84
Wei_Dai
6mo3 min readShow Highlight
35

A general model of safety-oriented AI development

69
Wei_Dai
6mo1 min readΩ 1Show Highlight
8

Can corrigibility be learned safely?

73
Wei_Dai
8mo3 min readΩ 1Show Highlight
110

Multiplicity of "enlightenment" states and contemplative practices

92
Wei_Dai
9mo2 min readShow Highlight
4

Look for the Next Tech Gold Rush?

37
Wei_Dai
4y1 min readShow Highlight
115

Six Plausible Meta-Ethical Alternatives

36
Wei_Dai
4y2 min readShow Highlight
36

How can we get more and better LW contrarians?

58
Wei_Dai
7yShow Highlight
335

Ontological Crisis in Humans

44
Wei_Dai
6y3 min readShow Highlight
67
Load More...  

Recent Comments