Announcement
Aryaman Arora joins Anthropic’s interpretability team after Stanford Ph.D. defense
Arora shared defense slides titled “Causal Interpretability for Analysing and Improving Language Model Architectures.”
TLDR
Aryaman Arora said in October 2026 that he had defended his Ph.D. at Stanford NLP a few months earlier and recently started on Anthropic’s Interpretability team. He also shared slides from his defense and said he was excited to keep working on interpretability.
Combined views
9.7K
10 Sources, first seen ago
