Joe_Carlsmith

Karma: 3,282

Senior research analyst at Open Philanthropy. Doctorate in philosophy at the University of Oxford. Opinions my own.

Fake thinking and real thinking

Joe_Carlsmith28 Jan 2025 20:05 UTC

50 points

1 comment1 min readEA link

(joecarlsmith.substack.com)

Takes on “Alignment Faking in Large Language Models”

Joe_Carlsmith18 Dec 2024 18:22 UTC

65 points

1 comment1 min readEA link

Incentive design and capability elicitation

Joe_Carlsmith12 Nov 2024 20:56 UTC

9 points

0 comments1 min readEA link

Option control

Joe_Carlsmith4 Nov 2024 17:54 UTC

11 points

0 comments1 min readEA link

Motivation control

Joe_Carlsmith30 Oct 2024 17:15 UTC

18 points

0 comments1 min readEA link

How might we solve the alignment problem? (Part 1: Intro, summary, ontology)

Joe_Carlsmith28 Oct 2024 21:57 UTC

18 points

0 comments1 min readEA link

Video and transcript of presentation on Otherness and control in the age of AGI

Joe_Carlsmith8 Oct 2024 22:30 UTC

18 points

1 comment1 min readEA link

What is it to solve the alignment problem?

Joe_Carlsmith24 Aug 2024 21:19 UTC

32 points

1 comment1 min readEA link

Value fragility and AI takeover

Joe_Carlsmith5 Aug 2024 21:28 UTC

38 points

3 comments1 min readEA link

A framework for thinking about AI power-seeking

Joe_Carlsmith24 Jul 2024 22:41 UTC

44 points

11 comments1 min readEA link

Loving a world you don’t trust

Joe_Carlsmith18 Jun 2024 19:31 UTC

65 points

7 comments1 min readEA link

On “first critical tries” in AI alignment

Joe_Carlsmith5 Jun 2024 0:19 UTC

29 points

3 comments1 min readEA link

On attunement

Joe_Carlsmith25 Mar 2024 12:47 UTC

27 points

0 comments1 min readEA link

Video and transcript of presentation on Scheming AIs

Joe_Carlsmith22 Mar 2024 15:56 UTC

23 points

1 comment1 min readEA link

On green

Joe_Carlsmith21 Mar 2024 17:38 UTC

61 points

3 comments1 min readEA link

On the abolition of man

Joe_Carlsmith18 Jan 2024 18:17 UTC

71 points

4 comments1 min readEA link

Being nicer than Clippy

Joe_Carlsmith16 Jan 2024 19:44 UTC

25 points

3 comments1 min readEA link

An even deeper atheism

Joe_Carlsmith11 Jan 2024 17:28 UTC

25 points

2 comments1 min readEA link

Does AI risk “other” the AIs?

Joe_Carlsmith9 Jan 2024 17:51 UTC

23 points

3 comments1 min readEA link

When “yang” goes wrong

Joe_Carlsmith8 Jan 2024 16:35 UTC

57 points

1 comment1 min readEA link