Research

Alignment Archive

Read more about the Arcadia Alignment team's research below.

← Back to the Alignment team

All

Auto Alignment and RSI

Model Motivations and Science of RL

AI is increasingly capable of AI research and development. We study where automated alignment research stands today, where it fails, and where it differs from capabilities.

Papers

Papers

No papers yet.

Blog posts

Blog posts

AI speeds up 3rd party safety researchers by ~1.6x (via self-reports)

Oct 27, 2026

Lessons from building an automated research scaffold

Oct 2, 2026

Obstacles to the scalable oversight of auto-alignment research

Sep 16, 2026

Automated alignment runs are hard to study!

Aug 13, 2026

Want updates on our work? Join the mailing list →

Questions? Contact us →