x

LESSWRONG
LW

KevinOShaughnessy — LessWrong

KevinOShaughnessy

KevinOShaughnessy

Message

I'm a senior software engineer with 20 years experience who's concerned about AI safety. I bring practical engineering judgment, security mindset, and understanding of how real systems fail. I'm doing an MSc to formalize my ML knowledge and enter the field.

14

3

4

4mo

KevinOShaughnessy

I'm a senior software engineer with 20 years experience who's concerned about AI safety. I bring practical engineering judgment, security mindset, and understanding of how real systems fail. I'm doing an MSc to formalize my ML knowledge and enter the field.

What formal protocols should exist when a model under evaluation is used in the evaluation pipeline?

Following the criticisms listed by Yaniv Golan and Zvi Mowshowitz in response to the Opus 4.6 System Card https://medium.com/@yanivg/when-the-evaluator-becomes-the-evaluated-a-critical-analysis-of-the-claude-opus-4-6-system-card-258da70b8b37 https://thezvi.wordpress.com/2026/02/09/claude-opus-4-6-system-card-part-1-mundane-alignment-and-model-welfare/ and the brief commentary by Peter Wildeford https://x.com/peterwildeford/status/2019480244789387478 It is clear that this has already been acknowledged as a problem. Is this a problem that is being worked on in...

Roundup of recent interviews on AI

Over the past 6 months I've spent many many hours watching a variety of YouTube videos on the subject of AI and AI risk. As time is limited, I thought it'd be useful to present my favourites and give you my perspectives on the key points. I don't have a...

Nov 26, 2025•1