LLMpeople
Public Atlas People first, reports as evidence, organizations as context.

Atlas / People / Detail

Josh Batson

Josh Batson is a research scientist at Anthropic. Public descriptions of his work emphasize understanding how and why AI systems work, especially interpretability.

Research scientist at Anthropic.1 organizations2 reports

Profile status: updated

updated 1 public sources
mechanistic interpretabilityinterpretability

Current frame

Research scientist at Anthropic.

Work

Anthropic Research Scientist

Public links

other Lawfare contributor page

Organizations

core Anthropic

Reports

Alignment and Safety Auditing language models for hidden objectives Interpretability Tracing the thoughts of a large language model

Supporting sources

Josh Batson Supporting source · other · Lawfare