RSS

Joe Carlsmith

Karma: 3,594

Senior research analyst at Open Philanthropy. Recently completed a doctorate in philosophy at the University of Oxford. Opinions my own.

Pre­dictable up­dat­ing about AI risk

Joe Carlsmith8 May 2023 21:53 UTC
288 points
23 comments36 min readLW link

Gentle­ness and the ar­tifi­cial Other

Joe Carlsmith2 Jan 2024 18:21 UTC
264 points
31 comments11 min readLW link

Can you con­trol the past?

Joe Carlsmith27 Aug 2021 19:39 UTC
170 points
90 comments47 min readLW link1 review

On green

Joe Carlsmith21 Mar 2024 17:38 UTC
137 points
17 comments31 min readLW link

Deep athe­ism and AI risk

Joe Carlsmith4 Jan 2024 18:58 UTC
129 points
22 comments27 min readLW link

On in­finite ethics

Joe Carlsmith31 Jan 2022 7:04 UTC
124 points
70 comments51 min readLW link1 review

An even deeper atheism

Joe Carlsmith11 Jan 2024 17:28 UTC
124 points
47 comments15 min readLW link

On the limits of ideal­ized values

Joe Carlsmith22 Jun 2021 2:10 UTC
111 points
20 comments35 min readLW link

Be­ing nicer than Clippy

Joe Carlsmith16 Jan 2024 19:44 UTC
106 points
22 comments27 min readLW link

Ac­tu­ally pos­si­ble: thoughts on Utopia

Joe Carlsmith18 Jan 2021 8:27 UTC
87 points
7 comments13 min readLW link

On the abo­li­tion of man

Joe Carlsmith18 Jan 2024 18:17 UTC
86 points
18 comments41 min readLW link

Draft re­port on ex­is­ten­tial risk from power-seek­ing AI

Joe Carlsmith28 Apr 2021 21:41 UTC
85 points
23 comments1 min readLW link

Re­views of “Is power-seek­ing AI an ex­is­ten­tial risk?”

Joe Carlsmith16 Dec 2021 20:48 UTC
79 points
20 comments1 min readLW link

New re­port: “Schem­ing AIs: Will AIs fake al­ign­ment dur­ing train­ing in or­der to get power?”

Joe Carlsmith15 Nov 2023 17:16 UTC
79 points
26 comments30 min readLW link

Thoughts on be­ing mortal

Joe Carlsmith1 Jan 2021 19:17 UTC
78 points
5 comments6 min readLW link

Killing the ants

Joe Carlsmith7 Feb 2021 23:17 UTC
76 points
27 comments8 min readLW link1 review

When “yang” goes wrong

Joe Carlsmith8 Jan 2024 16:35 UTC
72 points
6 comments13 min readLW link

On sincerity

Joe Carlsmith23 Dec 2022 17:13 UTC
70 points
6 comments42 min readLW link

On attunement

Joe Carlsmith25 Mar 2024 12:47 UTC
59 points
6 comments22 min readLW link

Does AI risk “other” the AIs?

Joe Carlsmith9 Jan 2024 17:51 UTC
59 points
3 comments8 min readLW link