RSS

Artem Karpov

Karma: 161

NEST: Nas­cent En­coded Stegano­graphic Thoughts

Artem Karpov17 Feb 2026 7:55 UTC
20 points
8 comments13 min readLW link

Stegano­graphic Chains of Thought Are Low-Prob­a­bil­ity but High-Stakes: Ev­i­dence and Arguments

Artem Karpov11 Dec 2025 7:40 UTC
20 points
1 comment6 min readLW link

The Illeg­ible Chain-of-Thought Menagerie

Artem Karpov18 Nov 2025 12:01 UTC
3 points
0 comments8 min readLW link

artkpv’s Shortform

Artem Karpov12 Oct 2025 9:52 UTC
2 points
15 comments1 min readLW link

How dan­ger­ous is en­coded rea­son­ing?

Artem Karpov30 Jun 2025 11:54 UTC
17 points
0 comments10 min readLW link

Philo­soph­i­cal Jailbreaks: Demo of LLM Nihilism

Artem Karpov4 Jun 2025 12:03 UTC
3 points
0 comments5 min readLW link

The Stegano­graphic Po­ten­tials of Lan­guage Models

Artem Karpov, Tinuade and SCho
8 May 2025 11:23 UTC
9 points
0 comments1 min readLW link

CCS on com­pound sentences

Artem Karpov4 May 2024 12:23 UTC
6 points
0 comments9 min readLW link

In­duc­ing hu­man-like bi­ases in moral rea­son­ing LMs

Artem Karpov, Austin Meek, Bogdan Ionut Cirstea and SCho
20 Feb 2024 16:28 UTC
23 points
3 comments14 min readLW link

How im­por­tant is AI hack­ing as LLMs ad­vance?

Artem Karpov29 Jan 2024 18:41 UTC
1 point
0 comments6 min readLW link

My (naive) take on Risks from Learned Optimization

Artem Karpov31 Oct 2022 10:59 UTC
7 points
0 comments5 min readLW link