Bryan Chan
Independent AI safety researcher working on preventing model misalignment, evaluating emerging risks, and developing reliable safeguards.
Selected research
All researchRecent writing
All writing- After Interviewing 18 SPAR Mentee Applicants, I Stopped Looking for the “Strongest” Candidate
- Spent 10+ Iterations Designing my First Academic Poster and barely Planned for the Presentation
- Hot Takes on Risk Quantification in AI
- Can Inoculation Prompting Reduce Sycophancy
- The Observability Trilemma: Why Cheap AI Monitors Fail and the Geometry of Deception