Jack Lindsey is interested in understanding the cognition of modern language models to make them more reliable and aligned with human values.
How media typically covers Jack Lindsey
Based on 3 scored articles
Directly quoted in these articles
Researchers from five major AI organizations collaborated to replicate and extend work on tracing computational circuits in LLMs using attribution graphs, framing interpretability as analogous to biological sciences with applications to model prediction and debugging.
“Co-author discussing attribution graphs and interpretability methods as analogous to understanding biology”
Referenced in coverage
“Jack Lindsey leads Anthropic's Model Psychology team with background in theoretical neuroscience, mentoring residents.”
“Co-author of Anthropic research showing how harmful and benign payloads propagate differently across agent networks and identifying mitigation strategies.”
“Co-authored research on the Assistant Axis for stabilizing language model personas.”