Chloe Loughridge

Chloe Loughridge

Research Fellow at Anthropic

I'm currently a Research Fellow at Anthropic. I'm concerned that advanced AI systems may develop the ability to secretly pursue harmful goals of their own. I've been fortunate to collaborate with Joe Benton, Jon Kutasov, and Tyler Tracy on AI control research.

Previously

  • Trained a video generation transformer.
  • Served as first author on DafnyBench, in collaboration with Nada Amin and Max Tegmark.
  • Co-authored VerMCTS, a verifier-guided reasoning and synthesis approach. I also pitched a related startup idea to Sam Altman, which was later featured in a Harvard Business School case study.
  • Selected as a 2018 AI Grant Fellow (Nat Friedman & Daniel Gross), where I began doing independent AI research.

I earned my B.A. in Computer Science from Harvard University in May 2024.

I love connecting with thoughtful people who are curious about AI, research, and the future—feel free to reach out!