Akash

Karma: 4,486

Time-Time Tradeoffs

Akash10 Apr 2022 2:33 UTC

17 points

1 comment3 min readLW link

(forum.effectivealtruism.org)

Lifeguards

Akash15 Jun 2022 23:03 UTC

12 points

3 comments2 min readLW link

(forum.effectivealtruism.org)

Conversation with Eliezer: What do you want the system to do?

Akash25 Jun 2022 17:36 UTC

120 points

38 comments2 min readLW link

A summary of every Replacing Guilt post

Akash30 Jun 2022 0:46 UTC

31 points

3 comments10 min readLW link

(forum.effectivealtruism.org)

$500 bounty for alignment contest ideas

Akash30 Jun 2022 1:56 UTC

29 points

5 comments2 min readLW link

A summary of every “Highlights from the Sequences” post

Akash15 Jul 2022 23:01 UTC

94 points

7 comments17 min readLW link

Four questions I ask AI safety researchers

Akash17 Jul 2022 17:25 UTC

17 points

0 comments1 min readLW link

An unofficial “Highlights from the Sequences” tier list

Akash5 Sep 2022 14:07 UTC

29 points

1 comment5 min readLW link

AI Safety field-building projects I’d like to see

Akash11 Sep 2022 23:43 UTC

44 points

7 comments6 min readLW link

Understanding Conjecture: Notes from Connor Leahy interview

Akash15 Sep 2022 18:37 UTC

107 points

23 comments15 min readLW link

Apply for mentorship in AI Safety field-building

Akash17 Sep 2022 19:06 UTC

9 points

0 comments1 min readLW link

(forum.effectivealtruism.org)

Alignment Org Cheat Sheet

Akash and Thomas Larsen

20 Sep 2022 17:36 UTC

69 points

8 comments4 min readLW link

7 traps that (we think) new alignment researchers often fall into

Akash and Thomas Larsen

27 Sep 2022 23:13 UTC

174 points

10 comments4 min readLW link

Possible miracles

Akash and Thomas Larsen

9 Oct 2022 18:17 UTC

64 points

33 comments8 min readLW link

Consider trying Vivek Hebbar’s alignment exercises

Akash24 Oct 2022 19:46 UTC

38 points

1 comment4 min readLW link

Resources that (I think) new alignment researchers should know about

Akash28 Oct 2022 22:13 UTC

77 points

9 comments4 min readLW link

Instead of technical research, more people should focus on buying time

Akash, OliviaJ and Thomas Larsen

5 Nov 2022 20:43 UTC

100 points

45 comments14 min readLW link

Ways to buy time

Akash, OliviaJ and Thomas Larsen

12 Nov 2022 19:31 UTC

34 points

23 comments12 min readLW link

Announcing AI Alignment Awards: $100k research contests about goal misgeneralization & corrigibility

Akash and OliviaJ

22 Nov 2022 22:19 UTC

73 points

20 comments4 min readLW link

Podcast: Shoshannah Tekofsky on skilling up in AI safety, visiting Berkeley, and developing novel research ideas

Akash25 Nov 2022 20:47 UTC

37 points

2 comments9 min readLW link