RSS

Jonas Hallgren

Karma: 1,575

AI Safety person currently working on multi-agent coordination problems.

A Tax­on­omy of Agents: In­tro & Re­quest for feedback

Jonas Hallgren27 Mar 2026 10:03 UTC
13 points
4 comments3 min readLW link
(equilibria1.substack.com)

A Com­po­si­tional Philos­o­phy of Science for Agent Foundations

Jonas Hallgren6 Mar 2026 8:40 UTC
25 points
1 comment13 min readLW link
(equilibria1.substack.com)

Sys­temic Risks and Where to Find Them

Jonas Hallgren13 Feb 2026 10:51 UTC
14 points
0 comments20 min readLW link
(equilibria1.substack.com)

Spec­tral Sig­na­tures of Grad­ual Disempowerment

Jonas Hallgren6 Feb 2026 15:08 UTC
35 points
4 comments17 min readLW link
(equilibria1.substack.com)

The Atoms of Knowl­edge Aren’t Universal

Jonas Hallgren3 Feb 2026 10:52 UTC
19 points
4 comments13 min readLW link
(equilibria1.substack.com)

Crys­tals in NNs: Tech­ni­cal Com­pan­ion Piece

Jonas Hallgren28 Dec 2025 10:44 UTC
24 points
4 comments15 min readLW link

Have You Tried Think­ing About It As Crys­tals?

Jonas Hallgren28 Dec 2025 10:44 UTC
75 points
9 comments10 min readLW link

In­tu­ition Pump: The AI Society

Jonas Hallgren3 Dec 2025 9:00 UTC
17 points
0 comments5 min readLW link

Cancer; A Crime Story (and other tales of op­ti­miza­tion gone wrong)

Jonas Hallgren7 Nov 2025 7:09 UTC
19 points
2 comments12 min readLW link

Sys­tem Level Safety Evaluations

markov and Jonas Hallgren
29 Sep 2025 13:57 UTC
16 points
0 comments9 min readLW link
(equilibria1.substack.com)

A Lens on the Sharp Left Turn: Op­ti­miza­tion Slack

Jonas Hallgren16 Sep 2025 8:31 UTC
28 points
3 comments4 min readLW link

A Phy­logeny of Agents

Jonas Hallgren and markov
15 Aug 2025 10:47 UTC
40 points
12 comments6 min readLW link
(substack.com)

The Align­ment Map­ping Pro­gram: Forg­ing In­de­pen­dent Thinkers in AI Safety—A Pilot Retrospective

Alvin Ånestrand, Jonas Hallgren and Utilop
10 Jan 2025 16:22 UTC
31 points
0 comments4 min readLW link

Med­i­ta­tion in­sights as phase shifts in your self-model

Jonas Hallgren7 Jan 2025 10:09 UTC
15 points
3 comments3 min readLW link

Model In­tegrity: MAI on Value Alignment

Jonas Hallgren5 Dec 2024 17:11 UTC
6 points
11 comments1 min readLW link
(meaningalignment.substack.com)

Re­pro­gram­ing the Mind: Med­i­ta­tion as a Tool for Cog­ni­tive Optimization

Jonas Hallgren11 Jan 2024 12:03 UTC
34 points
3 comments11 min readLW link

How well does your re­search adress the the­ory-prac­tice gap?

Jonas Hallgren8 Nov 2023 11:27 UTC
20 points
0 comments10 min readLW link

Jonas Hal­l­gren’s Shortform

Jonas Hallgren11 Oct 2023 9:52 UTC
3 points
44 comments1 min readLW link

Ad­vice for new al­ign­ment peo­ple: Info Max

Jonas Hallgren30 May 2023 15:42 UTC
24 points
4 comments5 min readLW link

Re­spect for Boundaries as non-ar­bir­trary co­or­di­na­tion norms

Jonas Hallgren9 May 2023 19:42 UTC
9 points
3 comments7 min readLW link