RobinHa

Karma: 217

When capabilities work is the safe bet

RobinHa1 Jul 2026 20:53 UTC

32 points

0 comments1 min readLW link

(robinhaselhorst.com)

How far do open weights trail the frontier?

RobinHa18 Jun 2026 11:01 UTC

22 points

4 comments1 min readLW link

(robinhaselhorst.com)

You Can Catch Sleeper Agents by Teaching Another Model to Imitate Them

RobinHa10 Jun 2026 15:21 UTC

68 points

6 comments9 min readLW link

(robinhaselhorst.com)

RobinHa’s Shortform

RobinHa8 May 2026 0:23 UTC

2 points

6 comments1 min readLW link

InsanityBench: Cryptic Puzzles as a Probe for Lateral Thinking

RobinHa22 Feb 2026 14:20 UTC

48 points

1 comment4 min readLW link

(www.robinhaselhorst.com)

Gradient-Based Recovery of Memorized Diffusion Model Data

RobinHa1 Feb 2026 0:05 UTC

10 points

0 comments3 min readLW link

Quantifying Love and Hatred

RobinHa14 Jan 2026 20:40 UTC

10 points

8 comments1 min readLW link

The Case Against Continuous Chain-of-Thought (Neuralese)

RobinHa10 Jan 2026 20:32 UTC

11 points

8 comments5 min readLW link

GRPO is terrible

RobinHa1 Dec 2025 22:54 UTC

4 points

2 comments5 min readLW link

(robinhaselhorst.com)