| Sep 26, 2026 | The Curse of Multiple Mediators: Hidden Interaction Effects in Activation Patching was accepted as a spotlight paper at NeurIPS 2026. See you in Sydney! |
| Jun 25, 2026 | Released Interphyre, a 2D physics puzzle environment with level editing, full simulator state access, and intervention capabilities to support causal analysis and agentic experimentation. |
| Jun 01, 2026 | Started an internship at Basis Research Institute working with Rafal Urbaniak, Emily Bunnapradist, and Michelangelo Naim on probabilistic actual causality and its applications to LLM interpretability. |
| Apr 10, 2026 | Guest lecture on mechanistic interpretability for COMPSCI 690S: AI Alignment. Slides here. |
| Dec 07, 2025 | Presented our work on Detecting and Characterizing Planning in Language Models at the NeurIPS 2025 Mechanistic Interpretability Workshop. |
| Aug 22, 2025 | Presented our work on Detecting and Characterizing Planning in Language Models at the 2nd New England Mechanistic Interpretability (NEMI) Workshop. |
| Feb 27, 2025 | I am joining the 10th edition of AI Safety Camp. |
| May 06, 2024 | Passed the qualifier stage and am officially a Ph.D. candidate! |