Gunnar_Zarncke

Karma: 10,953

Software engineering, parenting, cognition, meditation, other
Linkedin, Facebook, Admonymous (anonymous feedback)

Parameters of Metacognition—The Anesthesia Patient

Gunnar_Zarncke9 Jan 2026 1:20 UTC

21 points

0 comments8 min readLW link

Unsupervised Agent Discovery

Gunnar_Zarncke22 Dec 2025 22:01 UTC

22 points

0 comments6 min readLW link

HERMES: Towards Efficient and Verifiable Mathematical Reasoning in LLMs

Gunnar_Zarncke1 Dec 2025 10:07 UTC

8 points

0 comments1 min readLW link

(arxiv.org)

AI Safety Interventions

Gunnar_Zarncke24 Nov 2025 22:28 UTC

29 points

0 comments10 min readLW link

Thou art rainbow: Consciousness as a Self-Referential Physical Process

Gunnar_Zarncke24 Nov 2025 22:23 UTC

28 points

13 comments7 min readLW link

Victor Taelin’s notes on Gemini 3

Gunnar_Zarncke18 Nov 2025 18:30 UTC

32 points

1 comment3 min readLW link

(x.com)

[Linkpost] Competing Motivations: When More Incentives Lead To Less Effort

Gunnar_Zarncke4 Nov 2025 23:02 UTC

11 points

0 comments1 min readLW link

(x.com)

When “HDMI-1” Lies To You

Gunnar_Zarncke30 Oct 2025 12:23 UTC

18 points

0 comments1 min readLW link

[Question] Is there a safe version of the common crawl?

Gunnar_Zarncke12 Aug 2025 14:56 UTC

22 points

6 comments1 min readLW link

[Linkpost] How Am I Getting Along with AI?

Gunnar_Zarncke18 Jul 2025 22:26 UTC

11 points

0 comments1 min readLW link

(jessiefischbein.substack.com)

Hybrid model reveals people act less rationally in complex games, more predictably in simple ones

Gunnar_Zarncke9 Jul 2025 10:15 UTC

9 points

0 comments1 min readLW link

(arxiv.org)

Project Vend: Can Claude run a small shop?

Gunnar_Zarncke30 Jun 2025 15:22 UTC

53 points

8 comments1 min readLW link

(www.anthropic.com)

[Linkpost] The lethal trifecta for AI agents: private data, untrusted content, and external communication

Gunnar_Zarncke17 Jun 2025 16:09 UTC

13 points

3 comments1 min readLW link

(simonwillison.net)

Unexpected Conscious Entities

Gunnar_Zarncke5 May 2025 22:14 UTC

34 points

7 comments6 min readLW link

[Linkpost] The value of initiating a pursuit in temporal decision-making

Gunnar_Zarncke27 Mar 2025 21:47 UTC

13 points

0 comments2 min readLW link

Mistral Large 2 (123B) seems to exhibit alignment faking

Marc Carauleanu, Diogo de Lucena, Gunnar_Zarncke, Cameron Berg, Judd Rosenblatt, Mike Vaiana and Trent Hodgeson

27 Mar 2025 15:39 UTC

81 points

4 comments13 min readLW link

Hamburg – ACX Meetups Everywhere Spring 2025

Gunnar_Zarncke25 Mar 2025 23:48 UTC

9 points

0 comments1 min readLW link

Reducing LLM deception at scale with self-other overlap fine-tuning

Marc Carauleanu, Diogo de Lucena, Gunnar_Zarncke, Judd Rosenblatt, Cameron Berg, Mike Vaiana and Trent Hodgeson

13 Mar 2025 19:09 UTC

162 points

46 comments6 min readLW link

RL, but don’t do anything I wouldn’t do

Gunnar_Zarncke7 Dec 2024 22:54 UTC

63 points

5 comments1 min readLW link

(arxiv.org)

[Linkpost] Building Altruistic and Moral AI Agent with Brain-inspired Affective Empathy Mechanisms

Gunnar_Zarncke4 Nov 2024 10:15 UTC

13 points

0 comments1 min readLW link

(arxiv.org)