RSS

Vivek Hebbar

Karma: 1,104

How can we solve diffuse threats like re­search sab­o­tage with AI con­trol?

Vivek HebbarApr 30, 2025, 7:23 PM
43 points
0 comments8 min readLW link

How train­ing-gamers might func­tion (and win)

Vivek HebbarApr 11, 2025, 9:26 PM
105 points
5 comments13 min readLW link

Differ­ent senses in which two AIs can be “the same”

Jun 24, 2024, 3:16 AM
69 points
2 comments4 min readLW link

Thomas Kwa’s MIRI re­search experience

Oct 2, 2023, 4:42 PM
173 points
53 comments1 min readLW link

In­finite-width MLPs as an “en­sem­ble prior”

Vivek HebbarMay 12, 2023, 11:45 AM
46 points
0 comments5 min readLW link

[Question] Is EDT cor­rect? Does “EDT” == “log­i­cal EDT” == “log­i­cal CDT”?

Vivek HebbarMay 8, 2023, 2:07 AM
13 points
2 comments1 min readLW link

Vivek Heb­bar’s Shortform

Vivek HebbarNov 24, 2022, 2:57 AM
4 points
5 commentsLW link

Path de­pen­dence in ML in­duc­tive biases

Sep 10, 2022, 1:38 AM
68 points
13 comments10 min readLW link

Hes­sian and Basin volume

Vivek HebbarJul 10, 2022, 6:59 AM
35 points
10 comments4 min readLW link

[Short ver­sion] In­for­ma­tion Loss --> Basin flatness

Vivek HebbarMay 21, 2022, 12:59 PM
12 points
0 comments1 min readLW link

In­for­ma­tion Loss --> Basin flatness

Vivek HebbarMay 21, 2022, 12:58 PM
62 points
31 comments7 min readLW link

Org an­nounce­ment: [AC]RC

Vivek HebbarApr 17, 2022, 5:24 PM
82 points
11 comments1 min readLW link

[Question] When peo­ple ask for your P(doom), do you give them your in­side view or your bet­ting odds?

Vivek HebbarMar 26, 2022, 11:08 PM
11 points
11 comments1 min readLW link

Trans­former in­duc­tive bi­ases & RASP

Vivek HebbarFeb 24, 2022, 12:42 AM
15 points
4 comments1 min readLW link
(proceedings.mlr.press)

[Question] Fa­vorite /​ most ob­scure re­search on un­der­stand­ing DNNs?

Vivek HebbarFeb 21, 2022, 5:49 AM
16 points
1 comment1 min readLW link

How com­plex are my­opic imi­ta­tors?

Vivek HebbarFeb 8, 2022, 12:00 PM
26 points
1 comment15 min readLW link