User Profile

Ω15040203

paulfchristiano's Posts

sorted by new
All Posts
Frontpage
Curated
Questions
Events
Meta

Learning with catastrophes

515h3 min readShow Highlight
0

Capability amplification

73d13 min readShow Highlight
1

The reward engineering problem

37d6 min readShow Highlight
1

Towards formalizing universality

610d18 min readShow Highlight
1

Directions and desiderata for AI alignment

1010d13 min readShow Highlight
1

Ambitious vs. narrow value learning

611d3 min readShow Highlight
0

AlphaGo Zero and capability amplification

615d2 min readShow Highlight
16

[Link] Supervising strong learners by amplifying weak experts

717d1 min readShow Highlight
0

Clarifying "AI Alignment"

152mo3 min readShow Highlight
41

Corrigibility

92mo6 min readShow Highlight
2

paulfchristiano's Comments