Arcadia Impact

Programmes

Alignment Research

Blog

About

get updates

Arcadia Impact

Arcadia Impact

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

Papers

Papers

Stress-Testing Alignment Midtraining

Sep 17, 2026

Blog posts

Blog posts

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

Oct 27, 2026

Labs’ current alignment plans seem terrible

Oct 12, 2026

Lessons from building an automated research scaffold

Oct 2, 2026

Alignment Midtraining Cracks Under Pressure

Sep 21, 2026

Obstacles to the scalable oversight of auto-alignment research

Sep 16, 2026

Automated alignment runs are hard to study!

Aug 13, 2026

Debate with Self-Play Best-of-N Optimization

Jul 9, 2026

Your Model Organisms Might Be Fried

Jun 18, 2026

Arcadia Impact

Registered charity in England and Wales (Charity Number: 1212323).

Programmes

LASR Labs

AI Governance Taskforce

Impact First

Research

Alignment

Programme Outputs

Organisation

About

Careers

Privacy Policy

Code of Conduct

Contact

Arcadia Impact

Registered charity in England and Wales (Charity Number: 1212323).

Programmes

LASR Labs

AI Governance Taskforce

Impact First

Research

Alignment

Programme Outputs

Organisation

About

Careers

Privacy Policy

Code of Conduct

Contact

Arcadia Impact

Registered charity in England and Wales (Charity Number: 1212323).

Programmes

LASR Labs

AI Governance Taskforce

Impact First

Research

Alignment

Programme Outputs

Organisation

About

Careers

Privacy Policy

Code of Conduct

Contact