x
This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
LW
Login
Daniel Tan's
Shortform
by
Daniel Tan
17th Jul 2024
1 min read
496
2
This is a special post for quick takes by
Daniel Tan
. Only they can create top-level comments. Comments here also appear on the
Quick Takes page
and
All Posts page
.
Rendering 0/496 comments, sorted by
top scoring
(show all)
Click to highlight new comments since:
Today at 12:52 PM
Moderation Log
More from
Daniel Tan
View more
Curated and popular this week
496
Comments
496
Daniel Tan's Shortform — LessWrong
Mentioned in
425
“Alignment Engineering” vs. “Misalignment Science”
243
RL creates split personas
146
Greater good arguments in AI safety
134
Risk from fitness-seeking AIs: mechanisms and mitigations
42
A Sober Look at Steering Vectors for LLMs
Load More (5/7)
Comment Permalink
Daniel Tan
2y
1
0
[Draft][Note] On Singular Learning Theory
Relevant links
AXRP with Daniel Murfet on
an SLT primer
Manifund grant proposal on
DevInterp research agenda
Daniel Murfet's
post on "simple != short"
Timaeus blogpost on
actionable research projects
DevInterp
repository for estimating LLC
Reply
See in context