RSS

TW123

Karma: 3,704

An Overview of Catas­trophic AI Risks

Center for AI SafetyAug 15, 2023, 9:52 PM
37 points
1 comment13 min readEA link
(www.safe.ai)

[MLSN #9] Ver­ify­ing large train­ing runs, se­cu­rity risks from LLM ac­cess to APIs, why nat­u­ral se­lec­tion may fa­vor AIs over humans

TW123Apr 11, 2023, 4:05 PM
18 points
0 comments6 min readEA link
(newsletter.mlsafety.org)

ThomasW’s Quick takes

TW123Mar 28, 2023, 12:17 PM
7 points
1 comment1 min readEA link

[MLSN #8]: Mechanis­tic in­ter­pretabil­ity, us­ing law to in­form AI al­ign­ment, scal­ing laws for proxy gaming

TW123Feb 20, 2023, 4:06 PM
25 points
0 comments4 min readEA link
(newsletter.mlsafety.org)

What’s the deal with AI con­scious­ness?

TW123Jan 11, 2023, 4:37 PM
33 points
0 comments1 min readEA link

“AI” is an indexical

TW123Jan 3, 2023, 10:00 PM
23 points
2 comments1 min readEA link

ML Safety Schol­ars Sum­mer 2022 Retrospective

TW123Nov 1, 2022, 3:09 AM
56 points
2 comments21 min readEA link

“A Creepy Feel­ing”: Nixon’s De­ci­sion to Disavow Biolog­i­cal Weapons

TW123Sep 30, 2022, 3:17 PM
48 points
3 comments17 min readEA link

Cover story on EA in Time magazine

TW123Aug 10, 2022, 3:26 PM
94 points
19 comments1 min readEA link
(time.com)

An­nounc­ing the In­tro­duc­tion to ML Safety Course

TW123Aug 6, 2022, 2:50 AM
136 points
4 comments7 min readEA link

$20K in Boun­ties for AI Safety Public Materials

TW123Aug 5, 2022, 2:57 AM
45 points
11 comments6 min readEA link

Dialec­tic of Enlightenment

TW123Jun 15, 2022, 4:58 AM
5 points
1 comment2 min readEA link
(monoskop.org)

You Don’t Need To Jus­tify Everything

TW123Jun 12, 2022, 6:36 PM
144 points
11 comments3 min readEA link

Open Prob­lems in AI X-Risk [PAIS #5]

TW123Jun 10, 2022, 2:22 AM
44 points
1 comment36 min readEA link

Perform Tractable Re­search While Avoid­ing Ca­pa­bil­ities Ex­ter­nal­ities [Prag­matic AI Safety #4]

TW123May 30, 2022, 8:37 PM
33 points
1 comment25 min readEA link

Com­plex Sys­tems for AI Safety [Prag­matic AI Safety #3]

TW123May 24, 2022, 12:04 AM
49 points
6 comments21 min readEA link

EA Hous­ing Slack

TW123May 14, 2022, 8:16 PM
38 points
8 comments2 min readEA link

Look Out The Window

TW123May 12, 2022, 9:16 PM
77 points
3 comments2 min readEA link

A Bird’s Eye View of the ML Field [Prag­matic AI Safety #2]

TW123May 9, 2022, 5:15 PM
97 points
2 comments35 min readEA link

In­tro­duc­tion to Prag­matic AI Safety [Prag­matic AI Safety #1]

TW123May 9, 2022, 5:02 PM
68 points
0 comments6 min readEA link