Past Fellows' Work

2026

Daniel Ben-Levi

Columbia University

Mentor: Raja Moreno, Etymologic

Project: Back to Basics: Formal Analysis Hints Improve Weak-to-Strong Monitoring

2026

Cailyn Min

Mentor: Tori Qiu, Carnegie Mellon University

Project: Incentivizing AI Evaluation through Insurance: A Mechanism Design Approach

2026

Carl Parkin

Mentor: Matthew Ford

Project: Saddling the Tiger: Trends and Critical Mechanisms in Nuclear Weapons Acquisition

2026

Noah Peters

University of Chicago

Mentor: Pedro Oliboni, University of Chicago

Project: A Formal Framework for Measuring Institutional Collapse under a Nuclear Winter Scenario

2026

Will Fowler

Mentor: Shahin Tajik

Project: Verifying Frontier-Model Training Compute from GPU Telemetry

2026

Justin Chen

University of Chicago

Mentor: Simon Goldstein, University of Hong Kong

Project: Tying Your Own Hands: Credible Commitment Tools for Frontier Safety Policies

2026

Talia Wilcox

Mentor: Decker Eveleth

Project: Not All Nukes Are Created Equal: Theater Nuclear Forces and Perceptions of Escalation

2026

Vira Kasprova

Mentor: Varun Chandrasekaran

Project: Oversight Under Compression: Measuring Information Loss in Agent Reports

2026

William Guo

University of Chicago

Mentor: Grant Ho, University of Chicago

Project: Evaluating LLM-Generated Attacks on Provenance-Based Intrusion Detectors

2026

Patrick Park

Princeton University

Mentor: Alex Wellerstein, Stevens Institute of Technology

Project: How Cold War Nuclear Espionage Can Help AI Evaluators

2026

Vainateya Rangaraju

University of Chicago

Mentor: William L. Anderson, Cooperative AI Foundation

Project: Towards Representational Steganography: Can Multi-Agent Latent Collaboration Undermine White-Box Monitors?

SECOND LOOK 2026

Anastasia Wei

UC Berkeley

Project: Replication write-up forthcoming

SECOND LOOK 2026

Arav Dhoot

Columbia University

Projects: LLM CoTs Remain Monitorable When Being Unfaithful Requires Computation
Where Does Hint-Following and Concealment Arise? A Case Study on OLMo-3 Checkpoints

SECOND LOOK 2026

Brandon Qi

UC Berkeley

Project: Replication write-up forthcoming

SECOND LOOK 2026

Christine Corry

UC Berkeley

Projects: Single Forward Pass Evals on Fable, Opus 5, and GPT-5.6-Sol
Yet Another Concerning Result on Astra’s No-CoT Capabilities

SECOND LOOK 2026

Finn Cairns

Dartmouth College

Projects: Internal State Control Is a General Property of LLMs
SFT Also Drives Safety Eval Results in Olmo 3

SECOND LOOK 2026

Jack Thompson

Princeton University

Project: Replication write-up forthcoming

SECOND LOOK 2026

Vanessa Ng

Georgia Institute of Technology

Project: Peer Preservation in LLMs: A Replication and Deep Dive

SECOND LOOK 2026

Xijia Che

University of Illinois Urbana-Champaign

Project: Confirming Claims of Superposition and Adversarial Examples in Toy Models

2025

Yixiong Hao

Computer Science, Georgia Institute of Technology '27

Mentor: Mantas Mazeika, Center for AI Safety

Project: We Need a Better Way to Evaluate Emergent Misalignment

2025

Will Anderson

CS, Data Science & Mathematics, University of Wisconsin-Madison '27

Mentor: Lewis Hammond, Oxford University / Cooperative AI Foundation

Project: Diffuse Attacks on Multiagent Systems

2025

Jo Jiao

Mathematics and Philosophy, University of Chicago '27

Mentor: James Evans, UChicago; Austin Koslowski, UChicago

Project: Narrow RL Induces Broad Behavior Changes in LLMs

2025

Daniel Allen

Political Science and Cultural Anthropology, Middlebury College '24

Mentor: Nicole Kikendall, Argonne National Laboratory

Project: Rethinking Biological Weapon Deterrence in the 21st Century

2025

Samara Shaz

MA Committee for International Relations, University of Chicago '26

Mentor: Thomas Fraise, SciencesPo

Project: Regime Change and Credibility: Implications of Democratic Backsliding on Deterrence

2025

Olivia Long

CS, Mathematics & Cognitive Science, Columbia University '27

Mentor: Carter Teplica, New York University

Project: The AI in the Mirror: LLM Self-Recognition in an Iterated Public Goods Game

2025

Atharva Nihlani

Computer Science, Brown University '26

Mentor: Michael Lepori, Brown University

Project: Eliciting Situational Awareness in Large Language Models Through Fine-Tuning

2025

Edmund Bu

EE, Mathematics & CS, UC San Diego '25

Mentor: Yossi Gandelsman, TTIC

Project: Interpreting ResNet-based CLIP via Neuron-Attention Decomposition

2025

Yilin Huang

Political Science and Mathematics, Amherst College '28

Mentor: Josh You, Epoch AI

Project: Position: Why AI R&D Benchmarks Need to Measure Research Judgement Separately

2025

Jay Kim

Computer Science, Williams College '26

Mentor: Joe O'Brien, IAPS

Project: Rethinking Priorities for Frontier AI Security

2025

Aditya Singh

Computational and Applied Mathematics & Statistics, University of Chicago '27

Mentor: Adam Karvonen, MATS

Project: Lessons from Studying Model Organisms of Hidden Behavior

2025

Yerin Yoon

MA International Relations, The Fletcher School at Tufts University '26

Mentor: Lami Kim, Asia-Pacific Center for Security Studies

Project: Alignment as Deterrence: The U.S.-ROK Policy Alignment and North Korea's Provocations (1993-2023)

2025

Jacopo Minniti

Computational Sciences, Minerva University '27

Mentor: Tim Rudner, NYU/CSET; Neil Band, Stanford University

Project: Uncertainty Aware Tree Search: Using LLM Internals to Allocate Exploration Budget

2024

Audrey Weckwerth

BA/MA Global Studies and International Relations, University of Chicago '25

Mentor: Christopher Twomey, Naval Postgraduate School

Project: Strait to Catastrophe: Perceptual Factors in US-China-Taiwan Defense Posture and Nuclear Escalation

2024

Amina Anowara

Chemical and Biological Engineering, Princeton University '25

Mentor: Junhong Chen, UChicago; Aaron Shi, UChicago

Project: Integration of Remote Floating Gate FET-based Biosensor with Millifluidic Systems for Point-of-Care Diagnostics

2024

Aryan Shrivastava

Mathematics, University of Chicago '26

Mentor: Jessica Hullman, Northwestern University

Project: Response Inconsistency of Large Language Models in High-Stakes Military Decision Making

2024

Rhea Kanuparthi

Political Science and Mathematics, University of Chicago '27

Mentor: Ankit Panda, Carnegie Endowment for International Peace

Project: Nukes and Ladders: India and Pakistan's Nuclear Evolution

2024

Simon Siskel

Political Science and Mathematics, University of Chicago '25

Mentor: Paul Bracken, Yale University

Project: Deterrence and Deescalation: U.S. Strategies for a Nuclear-Capable Iran

2024

Anastasia Wei

Physics and Data Science, Northwestern University '25

Mentor: Kiho Park, UChicago

Project: Locating Semantic Understanding: Semantically Similar Sentences in Large Language Models

2024

Sanyu Rajakumar

Computational Biology, Brown University '24

Mentor: Rudolf Laine, Oxford University

Project: Eliciting Situational Awareness in Large Language Models Through Fine-Tuning

2024

Sophia Lloyd-George

Physics, Philosophy & Computer Science, Brown University '25

Mentor: Bo Li, UIUC; Stephen Casper, MIT

Project: Breaking the Circuit Breaker: When Does Circuit Breaking Safety Unlearning Fail?

2024

Kevin Li

MA Committee on International Relations, University of Chicago '24

Mentor: Charles Glaser, MIT

Project: Tripolarity, Resolve, and Nuclear Risks

2024

Lavinia Cavalet

BA/MA Economics and International Relations, University of Chicago '25

Mentor: Austin Carson, UChicago

Project: To Arm or Not to Arm: an Arctic Dilemma

2024

James Rosenberger

Computational and Applied Mathematics & Statistics, University of Chicago '26

Mentor: Mihai Anitescu, UChicago

Project: Measuring Community Significance and State Vulnerability After Nuclear Winter

2024

Helena Tran

Mathematics, University of California Irvine '25

Mentor: Olli Järviniemi, University of Helsinki

Project: Situational Awareness and Consistency in Language Model Deception: a Simulated AI Company Assistant

2024

Robert Shin

Physics and Statistics, University of Chicago '27

Mentor: Carter Teplica, New York University

Project: Investigating Fourier Representations and Learned Algorithms within Grokked Transformers

2024

Melody Gui

Computer Science and Philosophy, University of Southern California '25

Mentor: Bo Li, UIUC; Stephen Casper, MIT

Project: Breaking the Circuit Breaker: When Does Circuit Breaking Safety Unlearning Fail?

2024

Abhay Katoch

Biotechnology, Queen's University at Kingston '25

Mentor: Jonathan Ozik, UChicago/Argonne

Project: Modeling the Optimal Distribution of Wastewater-Based Surveillance Techniques

2024

Jibang Wu

PhD Computer Science, University of Chicago

Mentor: Haifeng Xu, UChicago

Project: Grounded Persuasive Language Generation for Automated Marketing

2024

Austin Coffey

MPhil in Policy Analysis, RAND Pardee '26

Mentor: James Steinberg, Johns Hopkins University

Project: Managing Conflict in the South China Sea

2024

Julien Benchek

Political Science, Economics & Physics, University of Chicago '27

Project: Large Language Models Exhibit Cognitive Biases in Interactive Stock Trading Scenarios

2023

Allison Huang

Art, Technology, and Business of Innovation, USC '26

Mentor: Hadrien Pouget, Carnegie Endowment for International Peace

Project: Open-source Language Models: Identifying Contributing Factors and Future Trends

2023

Anisha Hisham

Master of Public Policy, University of Chicago '24

Mentor: Alexander Arroyo, UChicago

Project: Status of Adaptation to Climate Risk in Pakistan

2023

Carter Teplica

Mathematics, Columbia University '23

Mentor: Yibo Jiang, UChicago

Project: A Mechanistic Analysis of Counting in Distil-GPT2

2023

Coleman Snell

Moral Psychology & Philosophy, Cornell University '24

Mentor: Lara Mani, Centre for the Study of Existential Risk, Cambridge

Group Project: X-Risk Communications Strategy & Introductory XLab Material

2023

Duc Nguyen

Physics, University of Chicago '26

Mentor: Tiffany Shaw, UChicago

Project: Examining Temperature Fluctuations and Soot Deposition in Nuclear Winter

2023

Josephine Dodge

Mathematics & Economics, University of Chicago '25

Project: Effectiveness of Advance Market Commitments for Vaccines in Pandemic Preparedness

2023

Joshua Payne

Molecular Engineering & Biochemistry, University of Chicago '26

Mentor: Alex Kleinman, PanLabs

Project: Optimizing 3' UTR Sequences and Secondary Structures to Improve mRNA Vaccine Thermostability

2023

Julian Baldwin

BS/MS Computer Science, Northwestern University '24

Mentor: David Reber, UChicago

Project: Exploring the Limits of OthelloGPT's Emergent Representations

2023

Laura Messner

Economics & Mathematics, Columbia University '25

Mentor: Anton Korinek, University of Virginia

Project: AI, Automation, and Systemic Risks

2023

Miles Wang

Computer Science and Government, Harvard College '26

Mentor: Tony Wang, MIT

Project: Forbidden Facts: An Investigation of Competing Objectives in Llama-2

2023

Mishaal Lakhani

Social Sciences & Business, Minerva University '24

Mentor: Lara Mani, Centre for the Study of Existential Risk, Cambridge

Group Project: X-Risk Communications Strategy & Introductory XLab Material

2023

Oksana Vickers

Political Science & Russian/Eastern European Studies, University of Chicago '23

Mentor: Austin Carson, UChicago

Project: Risk Assessment of Russian Use of Tactical Nuclear Weapons

2023

Shuyuan Wang

CS, Philosophy & Fundamentals: Issues and Texts, University of Chicago '25

Mentor: Chenhao Tan, UChicago

Group Project: Building an AI Reflection Agent for Policy Deliberation

2023

Stephan Llerena

Juris Doctor, University of Michigan Law School '22

Mentor: José Jaime Villalobos, Legal Priorities Project

Project: Global Governance of High-Risk Artificial Intelligence

2023

Vincent Li

Computer Science, Yale University '26

Mentor: Nick Doiron, Determined AI

Project: Prompting Code Interpreter to Write Better Unit Tests on Quixbugs Functions

2023

Yuxin Ji

MA Computational Social Science, University of Chicago '24

Mentor: Chenhao Tan, UChicago

Group Project: Building an AI Reflection Agent for Policy Deliberation

2022

Sandro Del Rivo

Computer Science & Philosophy, University of Chicago '23

Mentor: Victor Veitch, UChicago

Project: Will AGI Learn Alien Concepts?

2022

Soren Dunn

Chemistry, Statistics & Data Science, University of Chicago '23

Mentor: Victor Veitch, UChicago

Project: Improving Evaluation of Factual Accuracy in Language Models

2022

Grant Harris

Economics & Computational and Applied Math, University of Chicago '25

Mentor: Ali Merali, Yale University

Project: Cooperative AI: A Primer

2022

Sudhamshu Hosamane

MA Computational Social Science, University of Chicago '23

Mentor: Munmun De Choudhury, Georgia Institute of Technology

Project: Effective Strategies to Tackle Misinformation on Messaging Apps

2022

Henry Josephson

Philosophy & Data Science, University of Chicago '25

Mentor: Cullen O'Keefe, OpenAI

Project: A California Effect for Artificial Intelligence

2022

Theo Ko

Computer Science & Computational and Applied Math, University of Chicago '24

Mentor: Claire Donnat, UChicago

Project: Assessing Fairness of a Blackbox Graph Neural Network Model Through Node Masking

2022

Nicole Mateo

Psychology & Critical Race and Ethnic Studies, University of Chicago '24

Mentor: Anna Reosti, American Bar Foundation

Project: Survey of POC and Impressions of AI Risk

2022

Jack Wippell

MA International Relations, University of Chicago '22

Mentor: Robert Trager, UCLA; Duncan Snidal, Oxford

Project: When Deviation is Not an Option: Lessons from Reykjavik on Zero-Fail Treaties

2022

Andrew Yang

Computer Science & Linguistics, University of Chicago '23

Mentor: Allyson Ettinger, UChicago

Project: Knowledge Graphs for Language Model Evaluation

2022

Freddie Yang

MA Research Methods, University of Chicago Harris School '23

Mentor: Allyson Ettinger, UChicago

Project: A Random Thought on Multi-task Learning and AI Existential Risks

What our fellows have built.

Be next year's cohort.