Dewi S.W. Gould

Researcher, Arcadia Impact Alignment

prof_pic.jpg

I am a researcher on the Arcadia Impact Alignment Project (in collaboration with the UK AISI alignment team). My research is motivated by understanding and reducing risks from increasingly capable AI systems.

Previously I…

  • Was an Astra Fellow at Redwood Research, working on general purpose elicitation and no-CoT time horizons.
  • Was a post-doc at the Alan Turing Institute on Project Bluebird, working on synthetic scenario generation for autonomous air-traffic control. I gave a Pint of Science talk about it.
  • Did a PhD in mathematical physics at the University of Oxford. My thesis was on Generalized Symmetries in String Theory Realizations of Quantum Field Theories. I wrote a blog post about my research.

news

Jul 08, 2026 New blog post Debate with Self-Play Best-of-N Optimization on LessWrong.
Jun 04, 2026 New paper Think Fast: Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models out on arXiv.
May 11, 2026 Started new role as a researcher on the Arcadia Impact Alignment Project in London, UK :gb:.

recent research

  1. debate.png
    Debate with Self-Play Best-of-N Optimization
    Dewi S. W. Gould, Sam Martin, Alejandro Aristizabal, and 2 more authors
    2026
    Blog post, LessWrong
  2. think_fast.png
    Think Fast: Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models
    Dewi S. W. Gould, Francis Rhys Ward, Anders Cairns Woodruff, and 18 more authors
    arXiv preprint, 2026
  3. positive_case.png
    A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behavior
    H. Mayne, J. S. Kang, Dewi S. W. Gould, and 3 more authors
    In Proceedings of the 43rd International Conference on Machine Learning (ICML), 2026
  4. skate.png
    SKATE, a Scalable Tournament Eval: Weaker LLMs differentiate between stronger ones using verifiable challenges
    Dewi S. W. Gould, B. Mlodozeniec, and S. F. Brown
    arXiv preprint, 2025
  5. pac.png
    PAC Apprenticeship Learning with Bayesian Active Inverse Reinforcement Learning
    O. Bajgar, Dewi S. W. Gould, J. Liu, and 3 more authors
    In Reinforcement Learning Conference, 2025
    Earlier version at NeurIPS 2024 Workshop on Bayesian Decision-making and Uncertainty