- Role
- Member of Technical Staff
- Joined Anthropic
- Not public
- Before Anthropic
- Straight from university
Career
- Anthropic
- Member of Technical Staff; leads the Model Psychiatry team in interpretability
- Columbia University, Center for Theoretical Neuroscience
- PhD research
Education
- PhD, computational neuroscience, Columbia University (Center for Theoretical Neuroscience)
Sources1jlindsey15.github.io
Lesser-known facts
- Co-wrote the 2025 persona vectors paper on monitoring character traits in models.
- Built a computer chess player as a hobby project.
- Moved from brain research to AI because in a language model you can record every neuron, all the time, on any task.
- Did a 2021 practicum at Sandia National Laboratories modeling sequence memory with on-chip plasticity on Loihi.
- Contributed to Humanity's Last Exam, a benchmark of expert-level questions for testing language models.
- Found that Claude's "fear neurons" spike when a user casually mentions taking a dangerous dose of Tylenol.
- Cautioned that his emotion research does not show "the models are conscious or have feelings."
- Finds coding agents often give up on hard tasks, and that encouraging them makes them try harder.
Known for
- Persona vectors: Monitoring and controlling character traits in language models (2025)
- "Verbalizable Representations Form a Global Workspace in Language Models" (2026)
Sources1technologyreview.com
Interviews and talks
- Inner Cosmos with David Eagleman, Ep. 169: What Is Claude Thinking But Not Saying? (2026)eagleman.com
- Interview on AI psychology with Brink Lindsey (2026)brinklindsey.substack.com
