Steven Byrnes

Karma: 22,103

I’m an AGI safety / AI alignment researcher in Boston with a particular focus on brain algorithms. Research Fellow at Astera. See https://sjbyrnes.com/agi.html for a summary of my research and sorted list of writing. Physicist by training. Email: steven.byrnes@gmail.com. Leave me anonymous feedback here. I’m also at: RSS feed, X/Twitter, Bluesky, LinkedIn, and more at my website.

Incentive Learning vs Dead Sea Salt Experiment

Steven ByrnesJun 25, 2024, 5:49 PM

30 points

1 comment28 min readLW link

(Appetitive, Consummatory) ≈ (RL, reflex)

Steven ByrnesJun 15, 2024, 3:57 PM

38 points

1 comment3 min readLW link

[Valence series] 4. Valence & Liking / Admiring

Steven ByrnesJun 10, 2024, 2:19 PM

48 points

12 comments14 min readLW link

Response to nostalgebraist: proudly waving my moral-antirealist battle flag

Steven ByrnesMay 29, 2024, 4:48 PM

103 points

29 comments11 min readLW link

Spatial attention as a “tell” for empathetic simulation?

Steven ByrnesApr 26, 2024, 3:10 PM

55 points

12 comments8 min readLW link

A couple productivity tips for overthinkers

Steven ByrnesApr 20, 2024, 4:05 PM

78 points

13 comments4 min readLW link

“Artificial General Intelligence”: an extremely brief FAQ

Steven ByrnesMar 11, 2024, 5:49 PM

74 points

6 comments2 min readLW link

Some (problematic) aesthetics of what constitutes good work in academia

Steven ByrnesMar 11, 2024, 5:47 PM

148 points

12 comments12 min readLW link

Woods’ new preprint on object permanence

Steven ByrnesMar 7, 2024, 9:29 PM

58 points

1 comment6 min readLW link

Social status part 2/2: everything else

Steven ByrnesMar 5, 2024, 4:29 PM

65 points

2 comments23 min readLW link

Social status part 1/2: negotiations over object-level preferences

Steven ByrnesMar 5, 2024, 4:29 PM

118 points

15 comments21 min readLW link

Four visions of Transformative AI success

Steven ByrnesJan 17, 2024, 8:45 PM

112 points

22 comments15 min readLW link

Deceptive AI ≠ Deceptively-aligned AI

Steven ByrnesJan 7, 2024, 4:55 PM

96 points

19 comments6 min readLW link

[Valence series] Appendix A: Hedonic tone / (dis)pleasure / (dis)liking

Steven ByrnesDec 20, 2023, 3:54 PM

18 points

0 comments13 min readLW link

[Valence series] 5. “Valence Disorders” in Mental Health & Personality

Steven ByrnesDec 18, 2023, 3:26 PM

45 points

12 comments13 min readLW link

[Valence series] 4. Valence & Social Status (deprecated)

Steven ByrnesDec 15, 2023, 2:24 PM

35 points

19 comments11 min readLW link

[Valence series] 3. Valence & Beliefs

Steven ByrnesDec 11, 2023, 8:21 PM

77 points

12 comments21 min readLW link 1 review

[Valence series] 2. Valence & Normativity

Steven ByrnesDec 7, 2023, 4:43 PM

88 points

7 comments28 min readLW link 1 review

[Valence series] 1. Introduction

Steven ByrnesDec 4, 2023, 3:40 PM

99 points

16 comments16 min readLW link 2 reviews

Thoughts on “AI is easy to control” by Pope & Belrose

Steven ByrnesDec 1, 2023, 5:30 PM

197 points

63 comments14 min readLW link 1 review