- Technical AI Safety
Activation steering and plateaus in language models
- Fellow:
- Francisco Ferreira da Silva
- Mentor:
- Stefan Heimersheim
Projects
Explore the projects our fellows work on with their mentors, cohort by cohort.
Q1 2026
Explore the projects, fellows, and mentors of Pivotal's 2026 Q1 Research Fellowship.
- AI Governance
Analysing the Shanghai Cooperation Organisation’s (SCO) evolution from “information security” to “AI governance” frameworks
- Fellow:
- Otto Barrow
- Mentor:
- Karson Elmgren
- Technical AI Governance
Analysis of the technical feasibility of MAIM’s compute-based deterrence
- Fellow:
- Felix Choussat
- Mentor:
- Oscar Delaney
- Output:
- Can the U.S. and China Deny AI?
- Biodefense
Automated adversarial red-teaming of frontier model CBRN safeguards, with particular focus on dual-use biological research
- Fellow:
- Austin Morrissey
- Mentors:
- Jasper Götting, Peter Peneder
- Technical AI Safety
Can LLMs develop goal misgeneralization without reward misspecification?
- Fellow:
- Jinzhou Wu
- Mentor:
- Elliott Thornley
- AI Governance
Capability-based model of AI-driven labor disruption
- Fellow:
- Fabio Marinello
- Mentor:
- Max Reddel
- Technical AI Safety
Chain-of-thought faithfulness explanations via counterfactual relevance
- Fellows:
- Divyansh Singhvi, Shikhar Shiromani
- Mentor:
- Noah Y. Siegel
- Technical AI Safety
Control protocols for AI agents in code-refactoring settings
- Fellows:
- Preeti Ravindra, Sree Sharvesh S S
- Mentor:
- Tyler Tracy
- Technical AI Safety
Digital Minds Policy Strategy
- Fellow:
- Austin Smith
- Mentor:
- Lucius Caviola
- Technical AI Safety
Evaluation of adversarial influence between models
- Fellow:
- Patricia Paskov
- Mentor:
- Lewis Hammond
- Technical AI Governance
GPU Fingerprinting for Location Verification
- Fellow:
- Wayne Tee
- Mentor:
- Jonathan Happel
- AI Governance
How China defines and operationalizes “AI risk”
- Fellow:
- Kar Mun Nicole Wong
- Mentor:
- Emmie Hine
- Technical AI Safety
How preference-learning objectives shape diversity in generative models
- Fellow:
- Motahareh Sohrabi
- Mentor:
- Dylan Hadfield-Menell
- Technical AI Safety
Improving human-AI coordination in collective intelligence and decision-making
- Fellow:
- Darius Kianersi
- Mentor:
- Lewis Hammond
- Technical AI Safety
Investigating weight-sparse transformer circuits
- Fellow:
- Arnau Marin
- Mentor:
- Stefan Heimersheim
- AI Governance
Legal contract compliance for autonomous AI agents
- Fellow:
- Joseph Marvin Imperial
- Mentor:
- Noam Kolt
- Technical AI Safety
Measuring propensity for egregious behavior in coding agents
- Fellow:
- Prakrat Agrawal
- Mentor:
- Jérémy Scheurer
- Technical AI Governance
Model Authenticity Guarantees
- Fellow:
- Sophia Abraham
- Mentor:
- Ben Bucknall
- Technical AI Safety
Neutrality+: Preference framework for RL agents amenable to shutdown
- Fellow:
- Alec Harris
- Mentor:
- Elliott Thornley
- Technical AI Governance
Overview of Chinese AI chip making
- Fellow:
- Veronika Blablová
- Mentor:
- Erich Grunewald
- AI Governance
Recommendations for Coordinated Vulnerability Disclosure (CVD) in AI
- Fellow:
- Amritanshu Prasad
- Mentor:
- Prof. Robert Trager
- Technical AI Safety
Robust Constitutional Alignment with Distributional Preference Learning
- Fellow:
- Zheng Hui
- Mentor:
- Dylan Hadfield-Menell
- Biodefense
Testing reproducibility of narrow biological AI tools with coding agents
- Fellow:
- Shiv Muthupandiyan
- Mentors:
- Peter Peneder, Jasper Götting
- AI Governance
UK and international AI digital sovereignty
- Fellow:
- Kasia Jakimowicz
- Mentor:
- Prof. Robert Trager
- Technical AI Safety
Understanding CoT Obfuscation
- Fellow:
- Reilly Haskins
- Mentors:
- Joshua Engels, Bilal Chughtai
- Technical AI Safety
What is meant by “embodiment” in AI and philosophy
- Fellow:
- Shuqin Ma
- Mentor:
- Patrick Butlin
Get involved
Join our team
Work with us directly to advance AI safety research. No roles are open at the moment. If you think you may be a good fit for the team, introduce yourself and we will reach out when something opens up.
Mentor top emerging researchers
Guide a fellow on a research project, share your expertise, and help them grow as a researcher. We handle recruitment, logistics, and day-to-day research support.
Participate in a fellowship
Join our in-person research fellowship in London and work with experienced mentors on AI safety, AI governance, AIxBio, or biodefense.