This is the personal website of Luke Marks.

I am reachable at marksluke076[at]gmail[dot]com.

Publications

• Interpreting reward model divergence in large language models
• Informal safety guarantees for simulated optimizers through extrapolation from partial simulations
• Forthcoming - Alignment regularization for sparse autoencoders

Other

• Received a grant from Lightspeed Grants in 2023.
• Became a Non-Trivial Fellow in 2023.
• I was a research fellow at Apart Researchin 2023.
• Became a Magnificent Grantee in 2024.
• Received a grant from BERI in 2024.

Interests

• Sparse autoencoders for interpretability
• Program synthesis for neural networks
• Mind uploading
• Anthropics
• Decision theory
• Homomorphic encryption