RSS

Steven Byrnes

Karma: 19,806

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 , Mastodon , Threads , GitHub , Wikipedia , Physics-StackExchange , LinkedIn

A short­com­ing of con­crete demon­stra­tions as AGI risk advocacy

Steven Byrnes11 Dec 2024 16:48 UTC
103 points
27 comments2 min readLW link

Neu­ro­science of hu­man so­cial in­stincts: a sketch

Steven Byrnes22 Nov 2024 16:16 UTC
55 points
0 comments31 min readLW link

[In­tu­itive self-mod­els] 8. Root­ing Out Free Will Intuitions

Steven Byrnes4 Nov 2024 18:16 UTC
64 points
16 comments24 min readLW link

[In­tu­itive self-mod­els] 7. Hear­ing Voices, and Other Hallucinations

Steven Byrnes29 Oct 2024 13:36 UTC
50 points
2 comments16 min readLW link

[In­tu­itive self-mod­els] 6. Awak­en­ing /​ En­light­en­ment /​ PNSE

Steven Byrnes22 Oct 2024 13:23 UTC
62 points
8 comments21 min readLW link

Against em­pa­thy-by-default

Steven Byrnes16 Oct 2024 16:38 UTC
60 points
24 comments7 min readLW link

[In­tu­itive self-mod­els] 5. Dis­so­ci­a­tive Iden­tity (Mul­ti­ple Per­son­al­ity) Disorder

Steven Byrnes15 Oct 2024 13:31 UTC
58 points
7 comments11 min readLW link

[In­tu­itive self-mod­els] 4. Trance

Steven Byrnes8 Oct 2024 13:30 UTC
75 points
7 comments24 min readLW link

[In­tu­itive self-mod­els] 3. The Homunculus

Steven Byrnes2 Oct 2024 15:20 UTC
75 points
36 comments25 min readLW link

[In­tu­itive self-mod­els] 2. Con­scious Awareness

Steven Byrnes25 Sep 2024 13:29 UTC
81 points
48 comments16 min readLW link

[In­tu­itive self-mod­els] 1. Preliminaries

Steven Byrnes19 Sep 2024 13:45 UTC
88 points
20 comments15 min readLW link

Re­sponse to Dileep Ge­orge: AGI safety war­rants plan­ning ahead

Steven Byrnes8 Jul 2024 15:27 UTC
27 points
7 comments27 min readLW link

In­cen­tive Learn­ing vs Dead Sea Salt Experiment

Steven Byrnes25 Jun 2024 17:49 UTC
27 points
1 comment28 min readLW link

(Ap­pet­i­tive, Con­sum­ma­tory) ≈ (RL, re­flex)

Steven Byrnes15 Jun 2024 15:57 UTC
38 points
1 comment3 min readLW link

[Valence se­ries] 4. Valence & Lik­ing /​ Admiring

Steven Byrnes10 Jun 2024 14:19 UTC
46 points
12 comments14 min readLW link

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

Steven Byrnes29 May 2024 16:48 UTC
102 points
29 comments11 min readLW link

Spa­tial at­ten­tion as a “tell” for em­pa­thetic simu­la­tion?

Steven Byrnes26 Apr 2024 15:10 UTC
55 points
12 comments8 min readLW link

A cou­ple pro­duc­tivity tips for overthinkers

Steven Byrnes20 Apr 2024 16:05 UTC
78 points
13 comments4 min readLW link

“Ar­tifi­cial Gen­eral In­tel­li­gence”: an ex­tremely brief FAQ

Steven Byrnes11 Mar 2024 17:49 UTC
70 points
6 comments2 min readLW link

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

Steven Byrnes11 Mar 2024 17:47 UTC
147 points
12 comments12 min readLW link