about me
I am a research scientist at Anthropic, where I started and lead the societal impacts team. Prior to that, I was the founding research director at the Stanford Institute for Human Centered AI (HAI). I did my PhD in Computational Neuroscience at NYU and obtained my BS in Electrical Engineering and Computer Science (EECS) from Berkeley. For fun, I surf, play bass with my band, and read widely across the humanities and social sciences.
research
Collective Constitutional AI: Aligning a Language Model with Public Input
FAccTlast author
Jun 2024Many-shot Jailbreaking
NeurIPS
Dec 2024The Capacity for Moral Self-Correction in Large Language Models
arXivfirst author
Feb 2023Red Teaming Language Models to Reduce Harms
arXivfirst author
Aug 2022Constitutional AI: Harmlessness from AI Feedback
arXivmiddle author - evals
Dec 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
arXivmiddle author - evals
Apr 2022
Which Economic Tasks are Performed with AI? Evidence from Millions of Claude Conversations
arXivlast author
Feb 2025Evaluating Feature Steering: A Case Study in Mitigating Social Biases
Anthropic Research Bloglast author
Oct 2024Towards Measuring the Representation of Subjective Global Opinions in Language Models
COLMlast author
Oct 2024Measuring the Persuasiveness of Language Models
Anthropic Research Bloglast author
Apr 2024Evaluating and Mitigating Discrimination in Language Model Decisions
NeurIPS Algorithmic Fairness Workshoplast author
Dec 2024Discovering Language Model Behaviors with Model-Written Evaluations
ACLmiddle author - evals
July 2023Beyond the Imitation Game: Quantifying and Extrapolating the Capabilities of Language Models
TMLRmiddle author - evals
May 2022
Anthropic Economic Index: Understanding AI’s Effects on the Economy Over Time
Anthropic Economic Indexlast author
Feb 2025Challenges in Evaluating AI Systems
Anthropic Research Blogfirst author
Oct 2023Opportunities and Risks of LLMs for Scalable Deliberation with Polis
arXivlast author
Jun 2023Testing and Mitigating Elections-related Risks from AI
Anthropic Research Blog
Jun 2024Predictability and Surprise in Large Generative Models
FAccTfirst author
Jun 2022Understanding the Capabilities, Limitations, and Societal Impact of Large Language Models
arXivlast author
Feb 2021The AI Index 2021 Annual Report
arXiv
Mar 2021
Neural and Perceptual Signatures of Efficient Sensory Coding
arXivfirst author
Feb 2016Efficient Sensory Encoding and Bayesian Inference with Heterogeneous Neural Populations
Neural Computationfirst author
Oct 2014Implicit Encoding of Prior Probabilities in Optimal Neural Populations
NeurIPSfirst author
Dec 2010
media
Exclusive: Anthropic's Index Tracks AI Economy
Feb 2025Axios
Which Economic Tasks are Performed with AI? Evidence from Millions of Claude Conversations
How Claude Uses AI to Identify New Threats
Dec 2024Platformer
Clio: Privacy-Preserving Insights into Real-World AI Use
What if Dario Amodei is Right About AI?
Apr 2024The Ezra Klein Show | The New York Times
Measuring the Persuasiveness of Language Models
The 3 Most Important AI Innovations of 2023
Dec 2023Time Magazine
Collective Constitutional AI: Aligning a Language Model with Public Input
Anthropic Leads Charge Against AI Bias and Discrimination With New Research
Dec 2023VentureBeat
Evaluating and Mitigating Discrimination in Language Model Decisions
What if We Could All Control AI?
Oct 2023The New York Times
Collective Constitutional AI: Aligning a Language Model with Public Input
When Hackers Descended to Test AI, They Found Flaws Aplenty
Aug 2023The New York Times
Red Teaming Language Models to Reduce Harms
Language Models Might be Able to Self-correct Biases—If You Ask Them
Mar 2023MIT Technology Review
The Capacity for Moral Self-Correction in Large Language Models
The Unpredictable Abilities Emerging From Large AI Models
Mar 2023Quanta Magazine
Predictability and Surprise in Large Generative Models
OpenAI & Stanford Researchers Call for Urgent Action to Address Harms of LLMs Like GPT-3
Feb 2021VentureBeat
Understanding the Capabilities, Limitations, and Societal Impact of Large Language Models
Starfish Enterprise: Finding RNA Patterns in Single Cells
Aug 2019Nature
Starfish: Open Source Image Based Transcriptomics and Proteomics Tools