Adam JermynMember of Technical Staff · AnthropicResearcher↗
Researcher
AnthropicMember of Technical Staff, Interpretability
Arora led the Matryoshka attribution study, which introduced a way to trace a language model’s answers to the internal components that helped produce them.[1] He also co-developed ReFT, a way to adapt a model to new tasks by changing its internal signals while leaving its original weights intact.[2]
AnthropicSep 2026-present
Transluce2025-2026
Redwood Research2022-2023Work and education history is primarily focused on AI-relevant roles and may not be comprehensive.
Based on public sources. If accuracy is important, verify details using the links or references.
For corrections, updates, or requests to remove information, contact us.