Matthew Shinkle

• Matthew Shinkle 3 Sep 2025 5:38 UTC

  3 points

  0

  in reply to: Neel Nanda’s comment on: How To Be­come A Mechanis­tic In­ter­pretabil­ity Researcher

  PIBBSS definitely does some mech interp, and I believe AI safety camp has some mech interp projects.

• Matthew Shinkle 3 Sep 2025 1:18 UTC

  4 points

  0

  on: How To Be­come A Mechanis­tic In­ter­pretabil­ity Researcher

  For people looking for MATS-like programs in other locations, with different timelines, etc. this page is a great resource for finding other training programs, a number of which (PIBBSS, Pivotal, LASR Labs, others) include mech interp research: https://​​www.aisafety.com/​​map

Au­tomat­ing AI Safety: What we can do today

• Matthew Shinkle 14 Jul 2025 18:59 UTC

  4 points

  0

  on: Open Thread—Sum­mer 2025

  Hello! Long-time lurker, planning to post research results on here in the near future. I’m a currently a PIBBSS research fellow, working on LLM interpretability relating to activation plateaus and deception probes. I’ll be joining Anna Leshinskaya’s Relational Cognition lab in the fall as a postdoc, working on moral reasoning in LLMs. Feel free to reach out if you have any ideas, questions, etc. on any of these topics!