Vivek Hebbar

Karma: 1,290

Supervised fine-tuning as a method for training-based AI control

Emil Ryd, Joe Benton and Vivek Hebbar

13 Nov 2025 22:25 UTC

39 points

0 comments18 min readLW link

When does training a model change its goals?

Vivek Hebbar and ryan_greenblatt

12 Jun 2025 18:43 UTC

78 points

3 comments15 min readLW link

Political sycophancy as a model organism of scheming

Alex Mallen and Vivek Hebbar

12 May 2025 17:49 UTC

40 points

0 comments14 min readLW link

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

Vivek Hebbar30 Apr 2025 19:23 UTC

52 points

1 comment8 min readLW link

How training-gamers might function (and win)

Vivek Hebbar11 Apr 2025 21:26 UTC

110 points

5 comments13 min readLW link

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

Vivek Hebbar and Buck

24 Jun 2024 3:16 UTC

75 points

3 comments4 min readLW link 1 review

Thomas Kwa’s MIRI research experience

Thomas Kwa, peterbarnett, Vivek Hebbar, Jeremy Gillen, Bird Concept and Raemon

2 Oct 2023 16:42 UTC

173 points

53 comments1 min readLW link

Infinite-width MLPs as an “ensemble prior”

Vivek Hebbar12 May 2023 11:45 UTC

46 points

0 comments5 min readLW link

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

Vivek Hebbar8 May 2023 2:07 UTC

13 points

2 comments1 min readLW link

Vivek Hebbar’s Shortform

Vivek Hebbar24 Nov 2022 2:57 UTC

4 points

8 comments1 min readLW link

Path dependence in ML inductive biases

Vivek Hebbar and evhub

10 Sep 2022 1:38 UTC

68 points

13 comments10 min readLW link

Hessian and Basin volume

Vivek Hebbar10 Jul 2022 6:59 UTC

36 points

10 comments4 min readLW link

[Short version] Information Loss --> Basin flatness

Vivek Hebbar21 May 2022 12:59 UTC

12 points

0 comments1 min readLW link

Information Loss --> Basin flatness

Vivek Hebbar21 May 2022 12:58 UTC

62 points

31 comments7 min readLW link

Org announcement: [AC]RC

Vivek Hebbar17 Apr 2022 17:24 UTC

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 Hebbar26 Mar 2022 23:08 UTC

11 points

11 comments1 min readLW link

Transformer inductive biases & RASP

Vivek Hebbar24 Feb 2022 0:42 UTC

15 points

4 comments1 min readLW link

(proceedings.mlr.press)

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

Vivek Hebbar21 Feb 2022 5:49 UTC

16 points

1 comment1 min readLW link

How complex are myopic imitators?

Vivek Hebbar8 Feb 2022 12:00 UTC

26 points

1 comment15 min readLW link