GET IN TOUCH

For Researchers

If you're working on AI safety, mechanistic interpretability, or related fields and are interested in collaboration, I'd love to hear from you. I'm particularly interested in:

  • Joint research projects

  • Data sharing for mechanistic analysis

  • Peer review and methodology validation

  • University affiliation opportunities

For Safety Teams

I maintain ongoing responsible disclosure relationships with major AI companies. If you're part of a safety team and would like to discuss findings relevant to your systems, please reach out through appropriate channels.

For the Broader Community

I'm committed to sharing research findings with the broader AI safety community through talks, workshops, and publications. If you're organizing events or looking for speakers on empirical AI safety research, I'm happy to participate.