Steven Byrnes

Karma: 22,276

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, Substack, LinkedIn, and more at my website.

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

I’m confused about innate smell neuroanatomy

Steven ByrnesNov 28, 2023, 8:49 PM

40 points

2 comments9 min readLW link

8 examples informing my pessimism on uploading without reverse engineering

Steven ByrnesNov 3, 2023, 8:03 PM

118 points

12 comments12 min readLW link

Late-talking kid part 3: gestalt language learning

Steven ByrnesOct 17, 2023, 2:00 AM

33 points

5 comments3 min readLW link

“X distracts from Y” as a thinly-disguised fight over group status / politics

Steven ByrnesSep 25, 2023, 3:18 PM

112 points

14 comments8 min readLW link

A Theory of Laughter—Follow-Up

Steven ByrnesSep 14, 2023, 3:35 PM

37 points

3 comments8 min readLW link

A Theory of Laughter

Steven ByrnesAug 23, 2023, 3:05 PM

102 points

14 comments28 min readLW link

Model of psychosis, take 2

Steven ByrnesAug 17, 2023, 7:11 PM

34 points

13 comments4 min readLW link

My checklist for publishing a blog post

Steven ByrnesAug 15, 2023, 3:04 PM

87 points

6 comments3 min readLW link

Lisa Feldman Barrett versus Paul Ekman on facial expressions & basic emotions

Steven ByrnesJul 19, 2023, 2:26 PM

31 points

15 comments15 min readLW link

Thoughts on “Process-Based Supervision”

Steven ByrnesJul 17, 2023, 2:08 PM

74 points

4 comments23 min readLW link

Munk AI debate: confusions and possible cruxes

Steven ByrnesJun 27, 2023, 2:18 PM

244 points

21 comments8 min readLW link

My side of an argument with Jacob Cannell about chip interconnect losses

Steven ByrnesJun 21, 2023, 1:33 PM

144 points

11 comments11 min readLW link

LeCun’s “A Path Towards Autonomous Machine Intelligence” has an unsolved technical alignment problem

Steven ByrnesMay 8, 2023, 7:35 PM

140 points

37 comments15 min readLW link

Connectomics seems great from an AI x-risk perspective

Steven ByrnesApr 30, 2023, 2:38 PM

101 points

7 comments10 min readLW link 1 review

AI doom from an LLM-plateau-ist perspective

Steven ByrnesApr 27, 2023, 1:58 PM

161 points

24 comments6 min readLW link

Is “FOXP2 speech & language disorder” really “FOXP2 forebrain fine-motor crappiness”?

Steven ByrnesMar 23, 2023, 4:09 PM

22 points

8 comments6 min readLW link

EAI Alignment Speaker Series #1: Challenges for Safe & Beneficial Brain-Like Artificial General Intelligence with Steve Byrnes

Curtis Huebner and Steven Byrnes

Mar 23, 2023, 2:32 PM

28 points

0 comments27 min readLW link

(youtu.be)

Plan for mediocre alignment of brain-like [model-based RL] AGI

Steven ByrnesMar 13, 2023, 2:11 PM

68 points

25 comments12 min readLW link

Why I’m not into the Free Energy Principle

Steven ByrnesMar 2, 2023, 7:27 PM

150 points

50 comments9 min readLW link 1 review