Fall 2025 Topics
Fall 2025 Topics
Biosecurity
The deployment of glycol vapours as a pandemic prevention tool.
Technical AI Safety
Create a benchmark using Inspect to measure a threat-model-relevant AI capability. Gain hands-on experience in capability assessment and scalable evaluation methodologies.
Prerequisites:
Proficiency in Python
Previous use of LLM APIs.
Biosecurity
Develop a scalable nasal swab biosurveillance program as a viable pandemic prevention tool.
Prerequisites:
Comfort with quantitative analysis and cost-benefit evaluation
Develop multi-site sampling functionality for a metagenomic pandemic simulator that estimates pathogen detection costs.
Prerequisites:
Basic statistical analysis skills and familiarity with R programming
Comfort with mathematical concepts including exponential growth and parameter estimation
AI Governance
How can governments measure the AI share of GDP as a means of tracking human disempowerment?
Prerequisites:
Some background in economics or statistics (though economics or statistics do not need to be your course / concentration).
Examples of Past Projects
“The Data of Gradual Disempowerment: Measuring Systemic Existential Risks from Incremental AI Development”
“The Safety and Efficacy of Continuous Low-Dose 222 nm Far-UVC for Indoor Pathogen Inactivation”
“Refusal Is More Than a Single Direction”
“Understanding Real-World AI Use: Towards Sharing User Interaction Data”
“A High-Level Comparative Analysis of Governance Structures at Frontier AGI Labs”
“Case Studies of Successful Alt-Protein Products in China and Southeast Asia”
Examples in Each Research Area
Technical AI Safety
Identifying AI Agents’ Bottlenecks on Evaluations at Scale via Automated Analysis.
Investigating the Robustness of Language Models Obtained by ‘Pre-Training with Human Preferences’.
How Do LLM Features Develop Through Pre-Training and Fine-Tuning?
How Robust Are White-Box Detectors?
Can We Understand the Differences Between Different Machine Learning Models Mechanistically?
—
Mapping Jailbreaks in LLMs
Investigating the Psychology of LLMs
Paraphrasing as a Tool for Preventing Self-Recognition in LLMs
Does Goal Valence Affect Alignment Faking in LLMs?
AI Governance
What Is the Most Realistic Mode of Governance for Autonomous Weapons Systems?
A Landscape Analysis of the AI Policy and Governance Working Group (AIPGWG)
How Could an Ombudsman Contribute to Effective Post-Market Monitoring of AI?
What Is an Appropriate Level of Access to AI User Interaction Data?
AGI Lab Boards: What Should the Makeup and Functions of the Boards That Govern AGI Labs Be?
A Landscape Analysis of the Collective Intelligence Project (CIP)
Regulators, Evaluators, or Watchdog: What Should the UK Government’s AI Safety Institute Look Like?
—
Bootstrapping Probabilistic Confidence in a Safety Claim
Strengthening Safety Cases Through Use of Multiple Independent Parallel Arguments
Bridging AI Governance Across the Atlantic: Strategies for UK–US Collaboration in a Shifting Global Landscape
How Can We Prevent Gradual Human Disempowerment from AI?
Shadow AI Governance: Mapping the Power of Non-Governmental AI Rulemakers
Biosecurity
DNA Synthesis Screening: How Do We Address the Current Uneven Geographic Distributions?
The Role of Genomic Surveillance in Scaling Up Pandemic Preparedness in LMICs
—
What Are the Primary Bottlenecks in the Implementation of Far-UVC Technology in Public Health Settings, and How Can We Effectively Address Them?
Overcoming Bottlenecks in the Development and Deployment of Next-Generation PPE
Global Health
What Are the Projected Levels of Air Pollution in LMICs, and How Do Different Sectors Contribute to This Pollution, Allowing for the Identification of High-Impact Regions and Effective Intervention Strategies?
Are There Interventions That Would Cost-Effectively Prevent Childhood Pneumonia in LMICs?
What Is the Effect of Global Health Interventions on Equilibrium Population Levels?
—
Barriers to Scaling Up TB Diagnostics and Treatments in LMICs
Evaluating the Effectiveness of Heat Adaptation Strategies in Reducing Mortality in LMICs
Animal Welfare
Which Food Corporations Should Good Growth Target to Maximize Their Impact on Alternative Protein Adoption and Animal Welfare in Southeast Asia?
Identifying Case Studies of Successful Alt Protein Products in China and Southeast Asia
—
Animal Byproducts in Pet Food: How Does the Livestock Sector Profit from Byproducts?
What Drives Social Movements to a Tipping Point? Lessons for the Animal Advocacy Movement
How Cost-Effective Is Corporate Litigation and Other Legal Advocacy Interventions?
How Generalizable Is Evidence on the Effectiveness of Corporate Outreach to the Global South?