RSS

Steven Byrnes

Karma: 3,439

Working on AGI safety via a deep-dive into brain algorithms, see https://​​sjbyrnes.com/​​agi.html

Solv­ing the whole AGI con­trol prob­lem, ver­sion 0.0001

Steven Byrnes8 Apr 2021 15:14 UTC
39 points
4 comments26 min readLW link

My AGI Threat Model: Misal­igned Model-Based RL Agent

Steven Byrnes25 Mar 2021 13:45 UTC
61 points
27 comments16 min readLW link

Against evolu­tion as an anal­ogy for how hu­mans will cre­ate AGI

Steven Byrnes23 Mar 2021 12:29 UTC
38 points
25 comments25 min readLW link

Acetyl­choline = Learn­ing rate (aka plas­tic­ity)

Steven Byrnes18 Mar 2021 13:57 UTC
29 points
4 comments4 min readLW link

Is RL in­volved in sen­sory pro­cess­ing?

Steven Byrnes18 Mar 2021 13:57 UTC
13 points
4 comments5 min readLW link

Com­ments on “The Sin­gu­lar­ity is Nowhere Near”

Steven Byrnes16 Mar 2021 23:59 UTC
47 points
5 comments8 min readLW link

Book re­view: “A Thou­sand Brains” by Jeff Hawkins

Steven Byrnes4 Mar 2021 5:10 UTC
97 points
14 comments19 min readLW link

Full-time AGI Safety!

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

Late-talk­ing kids and “Ein­stein syn­drome”

Steven Byrnes3 Feb 2021 15:16 UTC
29 points
19 comments5 min readLW link

[U.S. spe­cific] PPP: free money for self-em­ployed & orgs (time-sen­si­tive)

Steven Byrnes9 Jan 2021 19:53 UTC
35 points
1 comment2 min readLW link

Multi-di­men­sional re­wards for AGI in­ter­pretabil­ity and control

Steven Byrnes4 Jan 2021 3:08 UTC
10 points
5 comments10 min readLW link

Con­ser­vatism in neo­cor­tex-like AGIs

Steven Byrnes8 Dec 2020 16:37 UTC
20 points
2 comments8 min readLW link

Su­per­vised learn­ing in the brain, part 4: com­pres­sion /​ filtering

Steven Byrnes5 Dec 2020 17:06 UTC
12 points
0 comments5 min readLW link

In­ner Align­ment in Salt-Starved Rats

Steven Byrnes19 Nov 2020 2:40 UTC
110 points
31 comments11 min readLW link

Su­per­vised learn­ing of out­puts in the brain

Steven Byrnes26 Oct 2020 14:32 UTC
25 points
7 comments10 min readLW link

“Lit­tle glimpses of em­pa­thy” as the foun­da­tion for so­cial emotions

Steven Byrnes22 Oct 2020 11:02 UTC
25 points
0 comments5 min readLW link

My com­pu­ta­tional frame­work for the brain

Steven Byrnes14 Sep 2020 14:19 UTC
122 points
25 comments12 min readLW link

Emo­tional valence vs RL re­ward: a video game analogy

Steven Byrnes3 Sep 2020 15:28 UTC
11 points
6 comments4 min readLW link

Three men­tal images from think­ing about AGI de­bate & corrigibility

Steven Byrnes3 Aug 2020 14:29 UTC
50 points
35 comments4 min readLW link

Can you get AGI from a Trans­former?

Steven Byrnes23 Jul 2020 15:27 UTC
84 points
28 comments11 min readLW link