RSS

Oxford Ra­tion­al­ish—Sept Pub with Light­ning Talks ⚡️

Sam18 Aug 2022 13:37 UTC
2 points
0 comments1 min readLW link

As­tral Codex Ten meetup in Prague [Oct 6]

Jiří Nádvorník18 Aug 2022 12:15 UTC
2 points
0 comments1 min readLW link

Play­ing Without Affordances

Alex Hollow18 Aug 2022 11:53 UTC
5 points
0 comments1 min readLW link
(alexhollow.wordpress.com)

Goal-di­rect­ed­ness: rel­a­tivis­ing complexity

Morgan_Rogers18 Aug 2022 9:48 UTC
2 points
0 comments11 min readLW link

Ban­ga­lore—ACX Mee­tups Every­where ’22 + Septem­ber Social

Nihalm18 Aug 2022 8:10 UTC
1 point
0 comments1 min readLW link

What’s up with the bad Meta pro­jects?

Yitz18 Aug 2022 5:34 UTC
16 points
8 comments1 min readLW link

Seat­tle ACX Every­where—Oc­to­ber 2022

Nikita Sokolsky18 Aug 2022 5:13 UTC
3 points
0 comments1 min readLW link

As­tral Codex Ten Mee­tups Every­where: Bos­ton 2022

robirahman18 Aug 2022 3:48 UTC
2 points
0 comments1 min readLW link

An­nounc­ing En­cul­tured AI: Build­ing a Video Game

18 Aug 2022 2:16 UTC
52 points
5 comments4 min readLW link

Detroit ACX Septem­ber Meetup

MattArnold18 Aug 2022 0:48 UTC
1 point
0 comments1 min readLW link

Matt Ygle­sias on AI Policy

Grant Demaree17 Aug 2022 23:57 UTC
21 points
0 comments1 min readLW link
(www.slowboring.com)

Spoons and My­ofas­cial Trig­ger Points

vitaliya17 Aug 2022 22:54 UTC
2 points
1 comment1 min readLW link

Con­crete Ad­vice for Form­ing In­side Views on AI Safety

Neel Nanda17 Aug 2022 22:02 UTC
16 points
1 comment10 min readLW link

Mee­tups Every­where 2022!

JS17 Aug 2022 21:54 UTC
1 point
0 comments1 min readLW link

Progress links and tweets, 2022-08-17

jasoncrawford17 Aug 2022 21:27 UTC
11 points
0 comments2 min readLW link
(rootsofprogress.org)

Con­di­tion­ing, Prompts, and Fine-Tuning

Adam Jermyn17 Aug 2022 20:52 UTC
23 points
1 comment4 min readLW link

The Core of the Align­ment Prob­lem is...

17 Aug 2022 20:07 UTC
26 points
4 comments9 min readLW link

[Question] Could the simu­la­tion ar­gu­ment also ap­ply to dreams?

Nathan112317 Aug 2022 19:55 UTC
5 points
0 comments3 min readLW link

In­ter­pretabil­ity Tools Are an At­tack Channel

Thane Ruthenis17 Aug 2022 18:47 UTC
24 points
13 comments1 min readLW link

Hu­man Mimicry Mainly Works When We’re Already Close

johnswentworth17 Aug 2022 18:41 UTC
42 points
7 comments5 min readLW link