FAR.AI Research
youtube · Follow ↗
Evals & red teamingAlignment & interpretability
Alignment workshops, evaluations, red teaming and research talks
- Type
- Organization channel
- Priority
- Tier 1 · core
- Perspective
- Research institute
- Best for
- Technical talks and workshop recordings
- Publishes
- Event-driven / recurring
- Editor's note
- Primary-source talks from FAR.AI and collaborators.
Recent from FAR.AI Research
- A Zero-Tolerance Approach to AI Deception | Chris Cundy & Adam Gleave (FAR.AI) 2026-11-09
- Git For AI Agents Allows Rewind, Fork And Audit | Simon Yu (Northeastern University) 2026-11-04
- Safe By Design AI: What Architects Know That We Don’t | Adam Kalai (RESI) 2026-11-03
- The AI Policy Window Is Open Now | Adam Gleave (FAR.AI) 2026-11-02
- Editing A Model’s Beliefs Without Breaking It | Shi Feng (George Washington University) 2026-10-30
- AIs Could Attack The Inference Engine To Escape Sandboxes | James Mickens (Harvard University) 2026-10-27