a research blog of sorts
RSS FeedWriting about AI, mechanistic interpretability, and whatever else I find worth thinking about.
Recent Posts
-
Threat Modeling with LLMs
Updated: at 01:51 AMPreliminary findings regarding the effectiveness of threat modeling with LLMs and other interesting parts of the process.
-
Mission Statement (of sorts)
Updated: at 01:26 AMIt's a mission statement of sorts.
-
A reflection on CMU REUSE
Published: at 02:31 PMA short reflection on my experience in the undergraduate summer research program at Carnegie Mellon.