Trenton Bricken

Anthropic

Member of Technical Staff

Links

Focus

Control, Model Organisms, Red-Teaming, Scheming and Deception

Stream

Anthropic

I'm a Member of Technical Staff on the Alignment Science team at Anthropic. I'm currently enabling Claude to automatically audit and detect misalignment.

About me

  • I have a PhD in Systems Biology from Harvard. My thesis was on "Sparse Representations in Biological and Artificial Neural Networks" in the Kreiman Lab with support from the NSF Graduate Research Fellowship. I also spent time at the Berkeley Redwood Center for Theoretical Neuroscience as a visiting researcher.
  • I graduated from Duke University in May 2020 with a self-made major in "Minds and Machines: Biological and Artificial Intelligence". I was lucky to attend as a Robertson Scholar, which provided full funding during all four years, including summer experiences.
  • At Duke, I spent a year doing research in Dr. Michael Lynch's Lab attempting to use machine learning to design new CRISPR guide RNAs for safer, more effective genome editing. Afterwards, I was affiliated with Dr. Debora Marks's Lab at Harvard Medical School applying deep learning to protein design. I also contributed to the IARPA Fun GCAT and DARPA Biostasis programs.