Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
RSS
Tamsin Leake
Karma:
2,589
I’m
Tamsin Leake
, co-founder and head of research at
Orthogonal
, doing
agent foundations
.
All
Posts
Comments
New
Top
Old
Page
1
Orthogonal: A new agent foundations alignment organization
Tamsin Leake
19 Apr 2023 20:17 UTC
207
points
4
comments
1
min read
LW
link
(orxl.org)
the QACI alignment plan: table of contents
Tamsin Leake
21 Mar 2023 20:22 UTC
102
points
0
comments
1
min read
LW
link
(carado.moe)
everything is okay
Tamsin Leake
23 Aug 2022 9:20 UTC
98
points
22
comments
7
min read
LW
link
2
reviews
(carado.moe)
continue working on hard alignment! don’t give up!
Tamsin Leake
24 Mar 2023 0:14 UTC
82
points
45
comments
1
min read
LW
link
(carado.moe)
publishing alignment research and exfohazards
Tamsin Leake
31 Oct 2022 18:02 UTC
80
points
12
comments
1
min read
LW
link
1
review
(carado.moe)
How LDT helps reduce the AI arms race
Tamsin Leake
10 Dec 2023 16:21 UTC
70
points
13
comments
4
min read
LW
link
(carado.moe)
We’re all in this together
Tamsin Leake
5 Dec 2023 13:57 UTC
68
points
65
comments
2
min read
LW
link
(carado.moe)
Orthogonal’s Formal-Goal Alignment theory of change
Tamsin Leake
5 May 2023 22:36 UTC
68
points
12
comments
4
min read
LW
link
(carado.moe)
So you want to save the world? An account in paladinhood
Tamsin Leake
22 Nov 2023 17:40 UTC
65
points
19
comments
15
min read
LW
link
(carado.moe)
my current outlook on AI risk mitigation
Tamsin Leake
3 Oct 2022 20:06 UTC
63
points
6
comments
11
min read
LW
link
(carado.moe)
your terminal values are complex and not objective
Tamsin Leake
13 Mar 2023 13:34 UTC
60
points
6
comments
2
min read
LW
link
(carado.moe)
so you think you’re not qualified to do technical alignment research?
Tamsin Leake
7 Feb 2023 1:54 UTC
55
points
7
comments
1
min read
LW
link
(carado.moe)
formal alignment: what it is, and some proposals
Tamsin Leake
29 Jan 2023 11:32 UTC
53
points
3
comments
1
min read
LW
link
(carado.moe)
a narrative explanation of the QACI alignment plan
Tamsin Leake
15 Feb 2023 3:28 UTC
53
points
29
comments
6
min read
LW
link
(carado.moe)
formalizing the QACI alignment formal-goal
Tamsin Leake
and
JuliaHP
10 Jun 2023 3:28 UTC
53
points
6
comments
14
min read
LW
link
(carado.moe)
state of my alignment research, and what needs work
Tamsin Leake
3 Mar 2023 10:28 UTC
51
points
0
comments
2
min read
LW
link
(carado.moe)
PreDCA: vanessa kosoy’s alignment protocol
Tamsin Leake
20 Aug 2022 10:03 UTC
50
points
8
comments
7
min read
LW
link
(carado.moe)
ethics and anthropics of homomorphically encrypted computations
Tamsin Leake
9 Sep 2022 10:49 UTC
47
points
49
comments
3
min read
LW
link
(carado.moe)
an Evangelion dialogue explaining the QACI alignment plan
Tamsin Leake
10 Jun 2023 3:28 UTC
45
points
15
comments
43
min read
LW
link
(carado.moe)
the Insulated Goal-Program idea
Tamsin Leake
13 Aug 2022 9:57 UTC
43
points
4
comments
2
min read
LW
link
(carado.moe)
Back to top
Next