Now

  • I've contributing to two research projects as part of the Supervised Program for Alignment Research (SPAR) program
    • 1. Regulatory Safeguards for Multi-Agent AI Failures
    • 2. Sovereign Compute Initiatives: Assessing the progress of national compute projects and their implications for frontier AI regulation
  • I'm just finishing BlueDot Impact's AI Safety courses - both Alignment and Governance. I highly recommend them!
  • Other stuff I'm enjoying: bouldering, hiking, reading, designing jewelry, 3D printing

Updated June 20, 2024