Archive
About
Search
Log In
Home
All
Wiki
Shortform
Recent
Comments
RSS
ThomasW
Karma:
3,683
AI governance/grantmaking. Formerly at the
Center for AI Safety
and Yale EA organizer.
All
Posts
Comments
New
Top
Old
Page
1
An Overview of Catastrophic AI Risks
Center for AI Safety
15 Aug 2023 21:52 UTC
37
points
1
comment
13
min read
EA
link
(www.safe.ai)
[MLSN #9] Verifying large training runs, security risks from LLM access to APIs, why natural selection may favor AIs over humans
ThomasW
11 Apr 2023 16:05 UTC
18
points
0
comments
6
min read
EA
link
(newsletter.mlsafety.org)
ThomasW’s Quick takes
ThomasW
28 Mar 2023 12:17 UTC
7
points
1
comment
1
min read
EA
link
[MLSN #8]: Mechanistic interpretability, using law to inform AI alignment, scaling laws for proxy gaming
ThomasW
20 Feb 2023 16:06 UTC
25
points
0
comments
4
min read
EA
link
(newsletter.mlsafety.org)
What’s the deal with AI consciousness?
ThomasW
11 Jan 2023 16:37 UTC
33
points
0
comments
1
min read
EA
link
“AI” is an indexical
ThomasW
3 Jan 2023 22:00 UTC
23
points
2
comments
1
min read
EA
link
Is EA an advanced, planning, strategically-aware power-seeking misaligned mesa-optimizer?
ThomasW
16 Dec 2022 17:07 UTC
39
points
5
comments
7
min read
EA
link
ML Safety Scholars Summer 2022 Retrospective
ThomasW
1 Nov 2022 3:09 UTC
56
points
2
comments
21
min read
EA
link
“A Creepy Feeling”: Nixon’s Decision to Disavow Biological Weapons
ThomasW
30 Sep 2022 15:17 UTC
48
points
3
comments
11
min read
EA
link
Cover story on EA in Time magazine
ThomasW
10 Aug 2022 15:26 UTC
94
points
19
comments
1
min read
EA
link
(time.com)
Announcing the Introduction to ML Safety Course
ThomasW
6 Aug 2022 2:50 UTC
136
points
4
comments
7
min read
EA
link
$20K in Bounties for AI Safety Public Materials
ThomasW
5 Aug 2022 2:57 UTC
45
points
11
comments
6
min read
EA
link
Dialectic of Enlightenment
ThomasW
15 Jun 2022 4:58 UTC
5
points
1
comment
2
min read
EA
link
(monoskop.org)
You Don’t Need To Justify Everything
ThomasW
12 Jun 2022 18:36 UTC
139
points
11
comments
3
min read
EA
link
Open Problems in AI X-Risk [PAIS #5]
ThomasW
10 Jun 2022 2:22 UTC
44
points
1
comment
36
min read
EA
link
Perform Tractable Research While Avoiding Capabilities Externalities [Pragmatic AI Safety #4]
ThomasW
30 May 2022 20:37 UTC
33
points
1
comment
26
min read
EA
link
Complex Systems for AI Safety [Pragmatic AI Safety #3]
ThomasW
24 May 2022 0:04 UTC
49
points
6
comments
21
min read
EA
link
EA Housing Slack
ThomasW
14 May 2022 20:16 UTC
38
points
8
comments
2
min read
EA
link
Look Out The Window
ThomasW
12 May 2022 21:16 UTC
74
points
3
comments
2
min read
EA
link
A Bird’s Eye View of the ML Field [Pragmatic AI Safety #2]
ThomasW
9 May 2022 17:15 UTC
97
points
2
comments
36
min read
EA
link
Back to top
Next