johnswentworth

Karma: 44,624

Some Experiments I’d Like Someone To Try With An Amnestic

johnswentworth4 May 2024 22:04 UTC

47 points

28 comments3 min readLW link

[Question] Examples of Highly Counterfactual Discoveries?

johnswentworth23 Apr 2024 22:19 UTC

178 points

92 comments1 min readLW link

Why Would Belief-States Have A Fractal Structure, And Why Would That Matter For Interpretability? An Explainer

johnswentworth and David Lorell

18 Apr 2024 0:27 UTC

170 points

18 comments7 min readLW link

Generalized Stat Mech: The Boltzmann Approach

David Lorell and johnswentworth

12 Apr 2024 17:47 UTC

67 points

7 comments20 min readLW link

How We Picture Bayesian Agents

johnswentworth and David Lorell

8 Apr 2024 18:12 UTC

65 points

11 comments7 min readLW link

Coherence of Caches and Agents

johnswentworth1 Apr 2024 23:04 UTC

74 points

7 comments11 min readLW link

Natural Latents: The Concepts

johnswentworth and David Lorell

20 Mar 2024 18:21 UTC

80 points

16 comments19 min readLW link

The Worst Form Of Government (Except For Everything Else We’ve Tried)

johnswentworth17 Mar 2024 18:11 UTC

140 points

46 comments4 min readLW link

The Parable Of The Fallen Pendulum—Part 2

johnswentworth12 Mar 2024 21:41 UTC

74 points

8 comments4 min readLW link

The Parable Of The Fallen Pendulum—Part 1

johnswentworth1 Mar 2024 0:25 UTC

111 points

32 comments2 min readLW link

Leading The Parade

johnswentworth31 Jan 2024 22:39 UTC

141 points

30 comments9 min readLW link

A Shutdown Problem Proposal

johnswentworth and David Lorell

21 Jan 2024 18:12 UTC

122 points

61 comments6 min readLW link

Some Vacation Photos

johnswentworth4 Jan 2024 17:15 UTC

78 points

0 comments1 min readLW link

Apologizing is a Core Rationalist Skill

johnswentworth2 Jan 2024 17:47 UTC

152 points

42 comments5 min readLW link

The Plan − 2023 Version

johnswentworth29 Dec 2023 23:34 UTC

146 points

39 comments31 min readLW link

Natural Latents: The Math

johnswentworth and David Lorell

27 Dec 2023 19:03 UTC

114 points

31 comments14 min readLW link

Talk: “AI Would Be A Lot Less Alarming If We Understood Agents”

johnswentworth17 Dec 2023 23:46 UTC

58 points

3 comments1 min readLW link

(www.youtube.com)

Principles For Product Liability (With Application To AI)

johnswentworth10 Dec 2023 21:27 UTC

37 points

55 comments10 min readLW link

What I Would Do If I Were Working On AI Governance

johnswentworth8 Dec 2023 6:43 UTC

109 points

32 comments10 min readLW link

On Trust

johnswentworth6 Dec 2023 19:19 UTC

44 points

24 comments4 min readLW link