RSS

Steven Byrnes

Karma: 17,217

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

Chang­ing the world through slack & hobbies

Steven Byrnes21 Jul 2022 18:11 UTC
258 points
13 comments10 min readLW link

Munk AI de­bate: con­fu­sions and pos­si­ble cruxes

Steven Byrnes27 Jun 2023 14:18 UTC
244 points
21 comments8 min readLW link

What does it take to defend the world against out-of-con­trol AGIs?

Steven Byrnes25 Oct 2022 14:47 UTC
194 points
47 comments30 min readLW link1 review

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

Steven Byrnes1 Dec 2023 17:30 UTC
189 points
55 comments13 min readLW link

Jeff Hawk­ins on neu­ro­mor­phic AGI within 20 years

Steven Byrnes15 Jul 2019 19:16 UTC
170 points
24 comments12 min readLW link

[In­tro to brain-like-AGI safety] 1. What’s the prob­lem & Why work on it now?

Steven Byrnes26 Jan 2022 15:23 UTC
150 points
19 comments24 min readLW link

My com­pu­ta­tional frame­work for the brain

Steven Byrnes14 Sep 2020 14:19 UTC
150 points
26 comments13 min readLW link1 review

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

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

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

Steven Byrnes21 Jun 2023 13:33 UTC
144 points
11 comments11 min readLW link

AI doom from an LLM-plateau-ist perspective

Steven Byrnes27 Apr 2023 13:58 UTC
144 points
23 comments6 min readLW link

Why I’m not into the Free En­ergy Principle

Steven Byrnes2 Mar 2023 19:27 UTC
138 points
48 comments9 min readLW link

In­ner Align­ment in Salt-Starved Rats

Steven Byrnes19 Nov 2020 2:40 UTC
137 points
39 comments11 min readLW link2 reviews

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

Steven Byrnes8 May 2023 19:35 UTC
131 points
37 comments15 min readLW link

Re­ward Is Not Enough

Steven Byrnes16 Jun 2021 13:52 UTC
120 points
19 comments10 min readLW link1 review

Full-time AGI Safety!

Steven Byrnes1 Mar 2021 12:42 UTC
117 points
3 comments1 min readLW link

Book re­view: “A Thou­sand Brains” by Jeff Hawkins

Steven Byrnes4 Mar 2021 5:10 UTC
116 points
18 comments19 min readLW link

Can you get AGI from a Trans­former?

Steven Byrnes23 Jul 2020 15:27 UTC
115 points
40 comments12 min readLW link

Four vi­sions of Trans­for­ma­tive AI success

Steven Byrnes17 Jan 2024 20:45 UTC
112 points
22 comments15 min readLW link

8 ex­am­ples in­form­ing my pes­simism on up­load­ing with­out re­verse engineering

Steven Byrnes3 Nov 2023 20:03 UTC
111 points
12 comments12 min readLW link

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

Steven Byrnes5 Mar 2024 16:29 UTC
109 points
15 comments21 min readLW link