I’m a technical AI Safety Researcher at Redwood Research.

Before that, I researched AI threat models and developed evaluations for self-improvement capabilities at METR.

I’m going to run a red team / blue team capture the flag game to stress test alignment faking detection. The red team tries to create alignment faking models that evade detection and are realistic. The blue team tries to catch them.

For more information, see the relevant post: https://www.alignmentforum.org/posts/jWFvsJnJieXnWBb9r/alignment-faking-ctfs-apply-to-my-mats-stream

I’m mostly looking for strong software engineers. ML engineering experience is a bonus but not required. I also especially enjoy working with people who have some amount of vision or at least curiosity for research directions. I’d like to help people grow into researchers with their own independent views and agendas.