RSS

Gunnar_Zarncke

Karma: 10,461

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

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

Gunnar_ZarnckeMar 27, 2025, 9:47 PM
13 points
0 comments2 min readLW link

Mis­tral Large 2 (123B) ex­hibits al­ign­ment faking

Mar 27, 2025, 3:39 PM
80 points
4 comments13 min readLW link

Ham­burg – ACX Mee­tups Every­where Spring 2025

Gunnar_ZarnckeMar 25, 2025, 11:48 PM
9 points
0 comments1 min readLW link

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

Mar 13, 2025, 7:09 PM
155 points
40 comments6 min readLW link

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

Gunnar_ZarnckeDec 7, 2024, 10:54 PM
63 points
5 comments1 min readLW link
(arxiv.org)

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

Gunnar_ZarnckeNov 4, 2024, 10:15 AM
13 points
0 comments1 min readLW link
(arxiv.org)

Con­scious­ness As Re­cur­sive Reflections

Gunnar_ZarnckeOct 5, 2024, 8:00 PM
7 points
2 comments1 min readLW link
(www.astralcodexten.com)

Hyperpolation

Gunnar_ZarnckeSep 15, 2024, 9:37 PM
22 points
6 comments1 min readLW link
(arxiv.org)

Ra­tion­al­ist Pu­rity Test

Gunnar_ZarnckeJul 9, 2024, 8:30 PM
−9 points
5 comments1 min readLW link
(ratpuritytest.com)

Bed Time Quests & Din­ner Games for 3-5 year olds

Jun 22, 2024, 7:53 AM
51 points
0 comments1 min readLW link
(kidquest.substack.com)

Towards Guaran­teed Safe AI: A Frame­work for En­sur­ing Ro­bust and Reli­able AI Systems

Gunnar_ZarnckeMay 16, 2024, 1:09 PM
51 points
20 comments1 min readLW link
(arxiv.org)

[Linkpost] Silver Bul­letin: For most peo­ple, poli­tics is about fit­ting in

Gunnar_ZarnckeMay 1, 2024, 6:12 PM
18 points
4 comments1 min readLW link
(www.natesilver.net)

KAN: Kol­mogorov-Arnold Networks

Gunnar_ZarnckeMay 1, 2024, 4:50 PM
18 points
15 comments1 min readLW link
(arxiv.org)

Claude 3 Opus can op­er­ate as a Tur­ing machine

Gunnar_ZarnckeApr 17, 2024, 8:41 AM
36 points
2 comments1 min readLW link
(twitter.com)

Leave No Con­text Be­hind—A Comment

Gunnar_ZarnckeApr 11, 2024, 10:50 PM
18 points
0 comments2 min readLW link

ain­telope pro­ject update

Gunnar_ZarnckeFeb 8, 2024, 6:32 PM
24 points
2 comments3 min readLW link

[Linkpost] Con­tra four-wheeled suit­cases, sort of

Gunnar_ZarnckeSep 12, 2023, 8:36 PM
18 points
4 comments1 min readLW link
(dynomight.substack.com)

Try­ing Agen­tGPT, an Au­toGPT variant

Gunnar_ZarnckeApr 13, 2023, 10:13 AM
10 points
9 comments1 min readLW link

[Question] What is good Cy­ber Se­cu­rity Ad­vice?

Gunnar_ZarnckeOct 24, 2022, 11:27 PM
30 points
12 comments2 min readLW link

[Fun][Link] Align­ment SMBC Comic

Gunnar_ZarnckeSep 9, 2022, 9:38 PM
7 points
2 comments1 min readLW link
(www.smbc-comics.com)