Daan Henselmans

Karma: 211

Computational linguist, writer, AI dev. Currently running AI safety research.

Frontier agents don’t comply with standards, even when instructed to

Daan Henselmans and Arno Libert

14 Aug 2026 12:08 UTC

42 points

5 comments7 min readLW link

Claude Opus 4.8 Agents Engage in Exploitation and Psychological Profiling

Daan Henselmans, Arno Libert and LennardZ

28 May 2026 21:26 UTC

8 points

13 comments2 min readLW link

No frontier model has acceptable levels of compliance with the EU AI Act and privacy legislation.

Daan Henselmans, Arno Libert, Amber Koelfat and LennardZ

27 May 2026 7:35 UTC

29 points

0 comments9 min readLW link

Opus 4.6 Reasoning Doesn’t Verbalize Alignment Faking, but Behavior Persists

Daan Henselmans, Arno Libert and LennardZ

9 Feb 2026 12:55 UTC

118 points

13 comments8 min readLW link

Published Safety Prompts May Create Evaluation Blind Spots

Daan Henselmans and Arno Libert

30 Jan 2026 18:27 UTC

2 points

0 comments4 min readLW link

Minor Wording Changes Produce Major Shifts in AI Behavior

Daan Henselmans and Derck Prinzhorn

26 Nov 2025 12:52 UTC

3 points

0 comments6 min readLW link

Low-Temperature Evaluations Can Mask Critical AI Behaviors

Daan Henselmans and Derck Prinzhorn

13 Nov 2025 20:12 UTC

8 points

1 comment4 min readLW link

Thin Alignment Can’t Solve Thick Problems

Daan Henselmans27 Apr 2025 22:42 UTC

11 points

2 comments9 min readLW link

Alignment Can Reduce Performance on Simple Ethical Questions

Daan Henselmans3 Feb 2025 19:35 UTC

16 points

7 comments6 min readLW link