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

Atlas / People / Detail

Deep Ganguli

Research scientist at Anthropic who leads the Societal Impacts team and works on AI evaluation, alignment, and societal impacts.

Research Scientist at Anthropic1 organizations6 reports

Profile status: updated

updated United States 1 public sources
AI evaluationAI alignmentsocietal impacts

Current frame

Research Scientist at Anthropic

Extended note

Deep Ganguli is a research scientist at Anthropic, where his personal homepage says he started and leads the Societal Impacts team. His public bio also lists earlier work as founding research director at the Stanford Institute for Human-Centered AI, a PhD in computational neuroscience from NYU, and a BS in electrical engineering and computer science from Berkeley.

Education

New York University PhD · Computational Neuroscience
University of California, Berkeley BS · Electrical Engineering and Computer Science

Work

Anthropic Research Scientist
Stanford Institute for Human-Centered AI Founding Research Director

Public links

website Personal homepage github GitHub google_scholar Google Scholar linkedin LinkedIn

Organizations

core Anthropic

Reports

Alignment and RLHF Constitutional AI: Harmlessness from AI Feedback Alignment and Safety Constitutional Classifiers++: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming Alignment and Safety Many-shot Jailbreaking Alignment and Safety Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training Interpretability Tracing the thoughts of a large language model Alignment and RLHF Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Official and primary sources

Deep Ganguli personal homepage Official source · homepage · Deep Ganguli