Joe Carlsmith

Karma: 4,420

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

Incentive design and capability elicitation

Joe Carlsmith12 Nov 2024 20:56 UTC

31 points

0 comments12 min readLW link

Option control

Joe Carlsmith4 Nov 2024 17:54 UTC

26 points

0 comments54 min readLW link

Motivation control

Joe Carlsmith30 Oct 2024 17:15 UTC

43 points

7 comments52 min readLW link

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

Joe Carlsmith28 Oct 2024 21:57 UTC

52 points

5 comments32 min readLW link

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

Joe Carlsmith8 Oct 2024 22:30 UTC

35 points

1 comment27 min readLW link

What is it to solve the alignment problem?

Joe Carlsmith24 Aug 2024 21:19 UTC

68 points

17 comments53 min readLW link

Value fragility and AI takeover

Joe Carlsmith5 Aug 2024 21:28 UTC

76 points

5 comments30 min readLW link

A framework for thinking about AI power-seeking

Joe Carlsmith24 Jul 2024 22:41 UTC

62 points

15 comments16 min readLW link

Loving a world you don’t trust

Joe Carlsmith18 Jun 2024 19:31 UTC

134 points

13 comments33 min readLW link

On “first critical tries” in AI alignment

Joe Carlsmith5 Jun 2024 0:19 UTC

54 points

8 comments14 min readLW link

On attunement

Joe Carlsmith25 Mar 2024 12:47 UTC

92 points

8 comments22 min readLW link

Video and transcript of presentation on Scheming AIs

Joe Carlsmith22 Mar 2024 15:52 UTC

32 points

1 comment32 min readLW link

On green

Joe Carlsmith21 Mar 2024 17:38 UTC

263 points

35 comments31 min readLW link

On the abolition of man

Joe Carlsmith18 Jan 2024 18:17 UTC

88 points

18 comments41 min readLW link

Being nicer than Clippy

Joe Carlsmith16 Jan 2024 19:44 UTC

109 points

32 comments27 min readLW link

An even deeper atheism

Joe Carlsmith11 Jan 2024 17:28 UTC

125 points

47 comments15 min readLW link

Does AI risk “other” the AIs?

Joe Carlsmith9 Jan 2024 17:51 UTC

59 points

3 comments8 min readLW link

When “yang” goes wrong

Joe Carlsmith8 Jan 2024 16:35 UTC

72 points

6 comments13 min readLW link

Deep atheism and AI risk

Joe Carlsmith4 Jan 2024 18:58 UTC

149 points

22 comments27 min readLW link

Gentleness and the artificial Other

Joe Carlsmith2 Jan 2024 18:21 UTC

291 points

33 comments11 min readLW link