Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
RSS
Dan Valentine
Karma:
134
All
Posts
Comments
New
Top
Old
Debating with More Persuasive LLMs Leads to More Truthful Answers
Akbir Khan
,
John Hughes
,
Dan Valentine
,
Sam Bowman
and
Ethan Perez
7 Feb 2024 21:28 UTC
87
points
14
comments
9
min read
LW
link
(arxiv.org)
Understanding mesa-optimization using toy models
tilmanr
,
rusheb
,
Guillaume Corlouer
,
Dan Valentine
,
afspies
,
mivanitskiy
and
Can
7 May 2023 17:00 UTC
42
points
2
comments
10
min read
LW
link
[workshop] Detecting out of distribution data
Dan Valentine
14 Dec 2022 3:25 UTC
2
points
0
comments
1
min read
LW
link
[Online] EA Toronto Monthly Social
Dan Valentine
5 Apr 2020 22:54 UTC
1
point
0
comments
1
min read
LW
link
SSC Dublin Meetup
Dan Valentine
15 Jan 2020 8:26 UTC
1
point
0
comments
1
min read
LW
link
Dublin SSC Meetup—Death and Self
Dan Valentine
9 Dec 2019 7:50 UTC
1
point
2
comments
1
min read
LW
link
SSC Dublin Meetup—Atypical Minds and Book Recommendations
Dan Valentine
11 Nov 2019 21:07 UTC
1
point
0
comments
1
min read
LW
link
LW/SSC Dublin: The Great Filter, Cities and Ambition, Lifehacks—Saturday November 2nd
Dan Valentine
28 Oct 2019 22:13 UTC
2
points
0
comments
1
min read
LW
link
Meditations on Moloch and Pair Debugging
Dan Valentine
1 Oct 2019 19:37 UTC
1
point
0
comments
1
min read
LW
link
Dublin SSC/LW/EA “Meetups Everywhere” Meetup
Dan Valentine
14 Sep 2019 2:51 UTC
3
points
0
comments
1
min read
LW
link
Back to top