RSS

RobertM

Karma: 2,413

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

The LessWrong 2022 Re­view: Re­view Phase

RobertM22 Dec 2023 3:23 UTC
58 points
7 comments2 min readLW link

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

RobertM14 Sep 2023 2:18 UTC
85 points
4 comments8 min readLW link

What is the op­ti­mal fron­tier for due dili­gence?

RobertM and Ruby
8 Sep 2023 18:20 UTC
41 points
1 comment1 min readLW link

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

Ruby and RobertM
5 Sep 2023 21:30 UTC
14 points
6 comments1 min readLW link

Whether LLMs “un­der­stand” any­thing is mostly a ter­minolog­i­cal dispute

RobertM9 Jul 2023 3:31 UTC
10 points
1 comment1 min readLW link

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

RobertM28 Jun 2023 20:31 UTC
54 points
17 comments3 min readLW link

Why liber­tar­i­ans are ad­vo­cat­ing for reg­u­la­tion on AI

RobertM14 Jun 2023 20:59 UTC
35 points
13 comments4 min readLW link

Tran­script of a pre­sen­ta­tion on catas­trophic risks from AI

RobertM5 May 2023 1:38 UTC
6 points
0 comments8 min readLW link

Re­cent Database Mi­gra­tion—Re­port Bugs

RobertM26 Apr 2023 22:19 UTC
38 points
2 comments1 min readLW link

[New LW Fea­ture] “De­bates”

Ruby, RobertM, GPT-4 and Claude+
1 Apr 2023 7:00 UTC
113 points
34 comments1 min readLW link

AI-as­sisted al­ign­ment pro­pos­als re­quire spe­cific de­com­po­si­tion of capabilities

RobertM30 Mar 2023 21:31 UTC
16 points
2 comments6 min readLW link

The Filan Cabi­net Pod­cast with Oliver Habryka—Transcript

MondSemmel and RobertM
14 Feb 2023 2:38 UTC
99 points
9 comments72 min readLW link

LW Filter Tags (Ra­tion­al­ity/​World Model­ing now pro­moted in Lat­est Posts)

Ruby and RobertM
28 Jan 2023 22:14 UTC
60 points
4 comments3 min readLW link

RobertM’s Shortform

RobertM25 Jan 2023 8:20 UTC
6 points
13 comments1 min readLW link

De­con­fus­ing “Ca­pa­bil­ities vs. Align­ment”

RobertM23 Jan 2023 4:46 UTC
27 points
7 comments2 min readLW link

pa­tio11′s “Ob­ser­va­tions from an EA-ad­ja­cent (?) char­i­ta­ble effort”

RobertM10 Dec 2022 0:27 UTC
43 points
0 comments1 min readLW link
(forum.effectivealtruism.org)

New Fea­ture: Col­lab­o­ra­tive edit­ing now sup­ports logged-out users

RobertM2 Dec 2022 2:41 UTC
10 points
0 comments1 min readLW link

Dan Luu on Fu­tur­ist Predictions

RobertM14 Sep 2022 3:01 UTC
50 points
9 comments5 min readLW link
(danluu.com)

My thoughts on di­rect work (and join­ing LessWrong)

RobertM16 Aug 2022 18:53 UTC
57 points
4 comments6 min readLW link

Keep your pro­tos in one repo

RobertM28 Apr 2022 15:53 UTC
5 points
4 comments5 min readLW link
(docs.protocall.dev)