RobertM

Karma: 4,298

LessWrong dev & admin as of July 5th, 2022.

Eliezer’s Lost Alignment Articles / The Arbital Sequence

Ruby and RobertM

Feb 20, 2025, 12:48 AM

207 points

9 comments5 min readLW link

Arbital has been imported to LessWrong

RobertM, jimrandomh, Ben Pace and Ruby

Feb 20, 2025, 12:47 AM

279 points

30 comments5 min readLW link

Corrigibility’s Desirability is Timing-Sensitive

RobertMDec 26, 2024, 10:24 PM

29 points

4 comments3 min readLW link

Re: Anthropic’s suggested SB-1047 amendments

RobertMJul 27, 2024, 10:32 PM

87 points

13 comments9 min readLW link

(www.documentcloud.org)

Enriched tab is now the default LW Frontpage experience for logged-in users

Ruby and RobertM

Jun 21, 2024, 12:09 AM

46 points

27 comments3 min readLW link

[New Feature] Your Subscribed Feed

Ruby and RobertM

Jun 11, 2024, 10:45 PM

77 points

13 comments4 min readLW link

Against “argument from overhang risk”

RobertMMay 16, 2024, 4:44 AM

30 points

11 comments5 min readLW link

LW Frontpage Experiments! (aka “Take the wheel, Shoggoth!”)

Ruby and RobertM

Apr 23, 2024, 3:58 AM

71 points

27 comments5 min readLW link

The LessWrong 2022 Review: Review Phase

RobertMDec 22, 2023, 3:23 AM

58 points

7 comments2 min readLW link

Highlights: Wentworth, Shah, and Murphy on “Retargeting the Search”

RobertMSep 14, 2023, 2:18 AM

85 points

4 comments8 min readLW link

What is the optimal frontier for due diligence?

RobertM and Ruby

Sep 8, 2023, 6:20 PM

41 points

1 comment1 min readLW link

Conversation about paradigms, intellectual progress, social consensus, and AI

Ruby and RobertM

Sep 5, 2023, 9:30 PM

14 points

6 comments1 min readLW link

Whether LLMs “understand” anything is mostly a terminological dispute

RobertMJul 9, 2023, 3:31 AM

10 points

1 comment1 min readLW link

A “weak” AGI may attempt an unlikely-to-succeed takeover

RobertMJun 28, 2023, 8:31 PM

56 points

17 comments3 min readLW link

Why libertarians are advocating for regulation on AI

RobertMJun 14, 2023, 8:59 PM

35 points

13 comments4 min readLW link

Transcript of a presentation on catastrophic risks from AI

RobertMMay 5, 2023, 1:38 AM

6 points

0 comments8 min readLW link

Recent Database Migration—Report Bugs

RobertMApr 26, 2023, 10:19 PM

38 points

2 comments1 min readLW link

[New LW Feature] “Debates”

Ruby, RobertM, GPT-4 and Claude+

Apr 1, 2023, 7:00 AM

121 points

35 comments1 min readLW link

AI-assisted alignment proposals require specific decomposition of capabilities

RobertMMar 30, 2023, 9:31 PM

16 points

2 comments6 min readLW link

The Filan Cabinet Podcast with Oliver Habryka—Transcript

MondSemmel and RobertM

Feb 14, 2023, 2:38 AM

101 points

9 comments72 min readLW link