RSS

Chris_Leong

Karma: 6,622

De­cou­pling vs Con­tex­tu­al­is­ing Norms

Chris_Leong14 May 2018 22:44 UTC
155 points
51 comments2 min readLW link3 reviews

Don’t Dis­miss Sim­ple Align­ment Approaches

Chris_Leong7 Oct 2023 0:35 UTC
127 points
8 comments4 min readLW link

No­tice When Peo­ple Are Direc­tion­ally Correct

Chris_Leong14 Jan 2024 14:12 UTC
121 points
7 comments2 min readLW link

On De­stroy­ing the World

Chris_Leong28 Sep 2020 7:38 UTC
78 points
86 comments5 min readLW link

Challenges with Break­ing into MIRI-Style Research

Chris_Leong17 Jan 2022 9:23 UTC
75 points
15 comments3 min readLW link

The World Ac­cord­ing to Do­minic Cummings

Chris_Leong14 Apr 2020 5:05 UTC
69 points
14 comments7 min readLW link

Google “We Have No Moat, And Nei­ther Does OpenAI”

Chris_Leong4 May 2023 18:23 UTC
61 points
28 comments1 min readLW link
(www.semianalysis.com)

[Question] What’s the the­ory of im­pact for ac­ti­va­tion vec­tors?

Chris_Leong11 Feb 2024 7:34 UTC
57 points
12 comments1 min readLW link

In­ter­views on Im­prov­ing the AI Safety Pipeline

Chris_Leong7 Dec 2021 12:03 UTC
55 points
15 comments17 min readLW link

[Question] Can we get an AI to do our al­ign­ment home­work for us?

Chris_Leong26 Feb 2024 7:56 UTC
53 points
33 comments1 min readLW link

The Ham­mer and the Dance

Chris_Leong20 Mar 2020 16:09 UTC
48 points
5 comments1 min readLW link
(medium.com)

Should ra­tio­nal­ity be a move­ment?

Chris_Leong20 Jun 2019 23:09 UTC
48 points
13 comments3 min readLW link

Gen­eral Thoughts on Less Wrong

Chris_Leong3 Apr 2022 4:09 UTC
44 points
14 comments2 min readLW link

The Sense-Mak­ing Web

Chris_Leong4 Jan 2021 6:17 UTC
41 points
21 comments6 min readLW link

[Question] Why is Bayesi­anism im­por­tant for ra­tio­nal­ity?

Chris_Leong1 Sep 2020 4:24 UTC
37 points
24 comments1 min readLW link

$1000 USD prize—Cir­cu­lar Depen­dency of Counterfactuals

Chris_Leong1 Jan 2022 9:43 UTC
37 points
102 comments4 min readLW link

Yann LeCun on AGI and AI Safety

Chris_Leong6 Aug 2023 21:56 UTC
37 points
13 comments1 min readLW link
(drive.google.com)

No op­tion to re­port spam

Chris_Leong3 Dec 2018 13:40 UTC
37 points
13 comments1 min readLW link

[Question] What does the launch of x.ai mean for AI Safety?

Chris_Leong12 Jul 2023 19:42 UTC
35 points
3 comments1 min readLW link

[Question] How strong is the ev­i­dence for hy­drox­y­chloro­quine?

Chris_Leong5 Apr 2020 9:32 UTC
35 points
14 comments1 min readLW link