RSS

habryka(Oliver Habryka)

Karma: 32,734

Running Lightcone Infrastructure, which runs LessWrong. You can reach me at habryka@lesswrong.com

“AI Safety for Fleshy Hu­mans” an AI Safety ex­plainer by Nicky Case

habryka3 May 2024 18:10 UTC
82 points
10 comments4 min readLW link
(aisafety.dance)

Goal ori­ented cog­ni­tion in “a sin­gle for­ward pass”

22 Apr 2024 5:03 UTC
19 points
14 comments26 min readLW link

Ex­press in­ter­est in an “FHI of the West”

habryka18 Apr 2024 3:32 UTC
264 points
41 comments3 min readLW link

Struc­tured Trans­parency: a frame­work for ad­dress­ing use/​mis-use trade-offs when shar­ing information

habryka11 Apr 2024 18:35 UTC
23 points
0 comments2 min readLW link
(arxiv.org)

LessWrong’s (first) album: I Have Been A Good Bing

1 Apr 2024 7:33 UTC
537 points
167 comments11 min readLW link

How use­ful is “AI Con­trol” as a fram­ing on AI X-Risk?

14 Mar 2024 18:06 UTC
68 points
4 comments34 min readLW link

Open Thread Spring 2024

habryka11 Mar 2024 19:17 UTC
22 points
150 comments1 min readLW link

[Question] Is a ran­dom box of gas pre­dictable af­ter 20 sec­onds?

24 Jan 2024 23:00 UTC
37 points
35 comments1 min readLW link

[Question] Will quan­tum ran­dom­ness af­fect the 2028 elec­tion?

24 Jan 2024 22:54 UTC
63 points
48 comments1 min readLW link

Vote in the LessWrong re­view! (LW 2022 Re­view vot­ing phase)

habryka17 Jan 2024 7:22 UTC
26 points
9 comments2 min readLW link

AI Im­pacts 2023 Ex­pert Sur­vey on Progress in AI

habryka5 Jan 2024 19:42 UTC
28 points
1 comment7 min readLW link
(wiki.aiimpacts.org)

Origi­nal­ity vs. Correctness

6 Dec 2023 18:51 UTC
60 points
16 comments25 min readLW link

The LessWrong 2022 Review

habryka5 Dec 2023 4:00 UTC
115 points
43 comments4 min readLW link

Open Thread – Win­ter 2023/​2024

habryka4 Dec 2023 22:59 UTC
35 points
160 comments1 min readLW link

Com­plex sys­tems re­search as a field (and its rele­vance to AI Align­ment)

1 Dec 2023 22:10 UTC
64 points
9 comments19 min readLW link

How use­ful is mechanis­tic in­ter­pretabil­ity?

1 Dec 2023 2:54 UTC
156 points
53 comments25 min readLW link

My techno-op­ti­mism [By Vi­talik Bu­terin]

habryka27 Nov 2023 23:53 UTC
102 points
16 comments2 min readLW link
(www.lesswrong.com)

“Epistemic range of mo­tion” and LessWrong moderation

27 Nov 2023 21:58 UTC
60 points
3 comments12 min readLW link

De­bate helps su­per­vise hu­man ex­perts [Paper]

habryka17 Nov 2023 5:25 UTC
29 points
6 comments1 min readLW link
(github.com)

How much to up­date on re­cent AI gov­er­nance moves?

16 Nov 2023 23:46 UTC
109 points
4 comments29 min readLW link