Lucy Farnik

profile_pic.jpeg

I’m a machine learning PhD student researching LLM robustness and interpretability.

I just finished a research internship at Jane Street.

Before that I did MATS (mentored by Neel Nanda from Google DeepMind), ARENA, and various other research placements. I’ve published at ICLR/ICML in areas ranging from RL theory to LLM interpretability. My work has been cited by Anthropic and OpenAI, and I’ve received over $100k in grants. My Erdős number is 4.

My previous background is in SWE: I started coding when I was 7 and became a senior dev at age 18.

I’m always excited to meet new people with similar research interests! My email is {firstname}{lastname} at gmail. You’re also welcome to send me anonymous advice/feedback.

selected publications

  1. Lucy Farnik, Tim Lawson, Conor Houghton, and 1 more author
    In Forty-second International Conference on Machine Learning, 2025
  2. Joar M. V. Skalse, Lucy Farnik, Sumeet R. Motwani, and 3 more authors
    In The Twelfth International Conference on Learning Representations, 2024
  3. Tim Lawson, Lucy Farnik, Conor Houghton, and 1 more author
    In The Thirteenth International Conference on Learning Representations, 2025