LESSWRONG
Login
HOME
SEQUENCES
CODEX
HPMOR
paulfchristiano
Send Message
Users Feeds
This user has no feeds associated with them
Posts
magical scoring
Crowdsourcing moderation without sacrificing quality
9 months ago
paulfchristiano
9
points
expand_less
Upvote
expand_more
Downvote
Comments
26
Optimizing the news feed
9 months ago
paulfchristiano
9
points
expand_less
Upvote
expand_more
Downvote
Comments
9
Recent AI control posts
9 months ago
paulfchristiano
12
points
expand_less
Upvote
expand_more
Downvote
Over at medium, I’m continuing to write about AI control; here’s a roundup from the last month. Strategy - Prosaic AI control argues that
Comments
20
If we can't lie to others, we will lie to ourselves
9 months ago
paulfchristiano
16
points
expand_less
Upvote
expand_more
Downvote
Comments
24
Less costly signaling
9 months ago
paulfchristiano
12
points
expand_less
Upvote
expand_more
Downvote
Comments
39
What is up with carbon dioxide and cognition? An offer
a year ago
paulfchristiano
26
points
expand_less
Upvote
expand_more
Downvote
One or two research groups have published work on carbon dioxide and cognition. The state of the published literature is confusing. Here i
Comments
44
My research priorities for AI control
2 years ago
paulfchristiano
17
points
expand_less
Upvote
expand_more
Downvote
I've been thinking about what research projects I should work on, and I've posted my current view. Naturally, I think these are also good pr
Comments
3
Experimental EA funding [crosspost]
2 years ago
paulfchristiano
12
points
expand_less
Upvote
expand_more
Downvote
Over the course of 2015, we will be distributing $10,000 to completed projects which we believe will have a significant long-term humanitari
Comments
1
Recent AI safety work
3 years ago
paulfchristiano
20
points
expand_less
Upvote
expand_more
Downvote
(Crossposted from ordinary ideas). I’ve recently been thinking about AI safety, and some of the writeups might be interesting to some LWe
Comments
6
Approval-directed agents
3 years ago
paulfchristiano
9
points
expand_less
Upvote
expand_more
Downvote
Most concern about AI comes down to the scariness of goal-oriented behavior. A common response to such concerns is “why would we give an AI
Comments
22
Load More...