Hi! I'm Alfie
I'm an individual living in the UK, currently building Formation Research. I aim to be an impactful computer scientist in the future.
As a researcher, I am interested in AI-enabled totalitarianism, authoritarianism, coups, and power concentration, and governance-informed solutions for these problems leveraging technical methods of verification and cooperation.
Links
Research
- Lamerton, A., & Roger, F. (2026). Narrow secret loyalty dodges black-box audits. Preprint. arXiv
- Kwon, J., Lamerton, A., Draganov, A., Banerjee, D., Schoen, B., Pistillo, M., Kokotajlo, D., Evans, O., Roger, F., & Davidson, T. (2026). AIs with secret loyalties are a serious but addressable threat. Preprint
- Lamerton, A. (2026). A survey of AI-driven power concentration. Formation Research. Preprint
- Lamerton, A. (2025). Lock-in [Sequence]. LessWrong
- Lamerton, A. (2024). In-context learning: an alignment survey. LessWrong
- Lamerton, A. (2024). A review of in-context learning hypotheses for automated AI alignment research. LessWrong