RSS

Rob Bensinger

Karma: 21,936

Communications @ MIRI. Unless otherwise indicated, my posts and comments here reflect my own views, and not necessarily my employer’s. (Though we agree about an awful lot.)

MIRI’s 2024 End-of-Year Update

Rob Bensinger3 Dec 2024 4:33 UTC
98 points
2 comments4 min readLW link

Re­sponse to Aschen­bren­ner’s “Si­tu­a­tional Aware­ness”

Rob Bensinger6 Jun 2024 22:57 UTC
194 points
27 comments3 min readLW link

When is a mind me?

Rob Bensinger17 Apr 2024 5:56 UTC
141 points
129 comments15 min readLW link

AI Views Snapshots

Rob Bensinger13 Dec 2023 0:45 UTC
142 points
61 comments1 min readLW link

An ar­tifi­cially struc­tured ar­gu­ment for ex­pect­ing AGI ruin

Rob Bensinger7 May 2023 21:52 UTC
91 points
26 comments19 min readLW link

AGI ruin mostly rests on strong claims about al­ign­ment and de­ploy­ment, not about society

Rob Bensinger24 Apr 2023 13:06 UTC
70 points
8 comments6 min readLW link

The ba­sic rea­sons I ex­pect AGI ruin

Rob Bensinger18 Apr 2023 3:37 UTC
186 points
73 comments14 min readLW link

Four mind­set dis­agree­ments be­hind ex­is­ten­tial risk dis­agree­ments in ML

Rob Bensinger11 Apr 2023 4:53 UTC
136 points
12 comments1 min readLW link

Yud­kowsky on AGI risk on the Ban­kless podcast

Rob Bensinger13 Mar 2023 0:42 UTC
83 points
5 comments1 min readLW link

Ele­ments of Ra­tion­al­ist Discourse

Rob Bensinger12 Feb 2023 7:58 UTC
222 points
49 comments3 min readLW link1 review

Thoughts on AGI or­ga­ni­za­tions and ca­pa­bil­ities work

7 Dec 2022 19:46 UTC
102 points
17 comments5 min readLW link

A challenge for AGI or­ga­ni­za­tions, and a challenge for readers

1 Dec 2022 23:11 UTC
301 points
33 comments2 min readLW link

A com­mon failure for foxes

Rob Bensinger14 Oct 2022 22:50 UTC
47 points
7 comments2 min readLW link

ITT-pass­ing and ci­vil­ity are good; “char­ity” is bad; steel­man­ning is niche

Rob Bensinger5 Jul 2022 0:15 UTC
161 points
36 comments6 min readLW link1 review

The in­or­di­nately slow spread of good AGI con­ver­sa­tions in ML

Rob Bensinger21 Jun 2022 16:09 UTC
173 points
62 comments8 min readLW link

On sav­ing one’s world

Rob Bensinger17 May 2022 19:53 UTC
192 points
4 comments1 min readLW link

Late 2021 MIRI Con­ver­sa­tions: AMA /​ Discussion

Rob Bensinger28 Feb 2022 20:03 UTC
119 points
199 comments1 min readLW link

An­i­mal welfare EA and per­sonal dietary options

Rob Bensinger5 Jan 2022 18:53 UTC
38 points
32 comments3 min readLW link

Some ab­stract, non-tech­ni­cal rea­sons to be non-max­i­mally-pes­simistic about AI alignment

Rob Bensinger12 Dec 2021 2:08 UTC
70 points
35 comments7 min readLW link

Con­ver­sa­tion on tech­nol­ogy fore­cast­ing and gradualism

9 Dec 2021 21:23 UTC
108 points
30 comments31 min readLW link