x
This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
AF
Login
TurnTrout's shortform
feed
by
TurnTrout
30th Jun 2019
1 min read
845
10
This is a special post for quick takes by
TurnTrout
. Only they can create top-level comments. Comments here also appear on the
Quick Takes page
and
All Posts page
.
More from
TurnTrout
View more
Curated and popular this week
302
Comments
845
Rendering 0/302 comments, sorted by
top scoring
(show all)
Click to highlight new comments since:
Today at 3:44 AM
Moderation Log
TurnTrout's shortform feed — AI Alignment Forum
There are 1 comments pending acceptance to the Alignment Forum.
View them on LessWrong.
Mentioned in
96
Reward is not the optimization target
59
Humans provide an untapped wealth of evidence about alignment
48
Many arguments for AI x-risk are wrong
46
Inner and outer alignment decompose one hard problem into two extremely hard problems
38
Pretraining on Aligned AI Data Dramatically Reduces Misalignment—Even After Post-Training
Load More (5/16)
Comment Permalink
TurnTrout
6y
1
0
Transparency Q: how hard would it be to ensure a neural network doesn't learn any explicit NANDs?
Reply
See in context