Orpheus16

Karma: 6,666

“Status” can be corrosive; here’s how I handle it

Orpheus16Jan 24, 2023, 1:25 AM

71 points

8 comments6 min readLW link

[Linkpost] TIME article: DeepMind’s CEO Helped Take AI Mainstream. Now He’s Urging Caution

Orpheus16Jan 21, 2023, 4:51 PM

58 points

2 comments3 min readLW link

(time.com)

Wentworth and Larsen on buying time

Orpheus16, Thomas Larsen and johnswentworth

Jan 9, 2023, 9:31 PM

74 points

6 comments12 min readLW link

[Linkpost] Jan Leike on three kinds of alignment taxes

Orpheus16Jan 6, 2023, 11:57 PM

27 points

2 comments3 min readLW link

(aligned.substack.com)

My thoughts on OpenAI’s alignment plan

Orpheus16Dec 30, 2022, 7:33 PM

55 points

3 comments20 min readLW link

An overview of some promising work by junior alignment researchers

Orpheus16Dec 26, 2022, 5:23 PM

34 points

0 comments4 min readLW link

Podcast: Tamera Lanham on AI risk, threat models, alignment proposals, externalized reasoning oversight, and working at Anthropic

Orpheus16Dec 20, 2022, 9:39 PM

18 points

2 comments11 min readLW link

12 career-related questions that may (or may not) be helpful for people interested in alignment research

Orpheus16Dec 12, 2022, 10:36 PM

20 points

0 comments2 min readLW link

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

Orpheus16Nov 25, 2022, 8:47 PM

37 points

2 comments9 min readLW link

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

Orpheus16 and OliviaJ

Nov 22, 2022, 10:19 PM

74 points

20 comments4 min readLW link

Ways to buy time

Orpheus16, OliviaJ and Thomas Larsen

Nov 12, 2022, 7:31 PM

34 points

23 comments12 min readLW link

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

Orpheus16, OliviaJ and Thomas Larsen

Nov 5, 2022, 8:43 PM

101 points

45 comments14 min readLW link

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

Orpheus16Oct 28, 2022, 10:13 PM

70 points

9 comments4 min readLW link

Consider trying Vivek Hebbar’s alignment exercises

Orpheus16Oct 24, 2022, 7:46 PM

38 points

1 comment4 min readLW link

Possible miracles

Orpheus16 and Thomas Larsen

Oct 9, 2022, 6:17 PM

64 points

34 comments8 min readLW link

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

Orpheus16 and Thomas Larsen

Sep 27, 2022, 11:13 PM

177 points

10 comments4 min readLW link

Alignment Org Cheat Sheet

Orpheus16 and Thomas Larsen

Sep 20, 2022, 5:36 PM

70 points

8 comments4 min readLW link

Apply for mentorship in AI Safety field-building

Orpheus16Sep 17, 2022, 7:06 PM

9 points

0 comments1 min readLW link

(forum.effectivealtruism.org)

Understanding Conjecture: Notes from Connor Leahy interview

Orpheus16Sep 15, 2022, 6:37 PM

107 points

23 comments15 min readLW link

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

Orpheus16Sep 11, 2022, 11:43 PM

46 points

8 comments6 min readLW link