PeopleofSuperintelligence

Researcher

Elliot Glazer

Elliot Glazer is a mathematician whose work spans set theory and the evaluation of AI’s mathematical reasoning. He published results on choice paradoxes, co-authored FrontierMath, and led its development at Epoch AI. He holds a Harvard mathematics Ph.D. under Hugh Woodin and helped assess o3-mini-high’s reasoning on FrontierMath problems. As of October 2026, he is Lead Mathematician at Principia Labs and works on AI-assisted mathematics.

Timeline

  1. 2022

    A choiceless box game

    In 2022, he identifies a choiceless version of the box game paradox, where players predict unknown real numbers with near-perfect accuracy despite lacking useful information.

  2. 2023

    Global choice in Zermelo set theory

    In 2023, he proves that Global Choice is not conservative over ZC in a paper about Zermelo set theory.

  3. 2024

    Co-authoring FrontierMath

    In November 2024, he co-authors FrontierMath, a benchmark of hundreds of original, expert-vetted mathematics problems. The paper reports that leading AI models solve under 2% of them.

  4. March 2025

    Leading FrontierMath

    In March 2025, he leads FrontierMath as Epoch AI’s lead mathematician and discusses an expert competition to measure how hard its problems are.

  5. June 2025

    Assessing o3-mini-high

    In June 2025, he co-authors an Epoch AI analysis of o3-mini-high’s reasoning on FrontierMath, using reviews by 14 mathematicians of 29 reasoning traces. He holds a Ph.D. in mathematics from Harvard under Hugh Woodin, with research in set theory and formal systems.

  6. February 2026

    Reflection principles in ZFU

    In February 2026, he co-authors a paper that separates the Collection, Reflection, and Partial Reflection principles in ZF with urelements.

  7. April 2026

    Milestones for mathematical AI

    In April 2026, he organizes the Milestones of Autonomous Mathematics Research workshop with Daniel Litt, Jacob Tsimerman, Alex Kontorovich, and Ravi Vakil. They set out to define useful milestones for AI-assisted mathematics.

  8. As of October 2026

    Principia Labs mathematics lead

    As of October 2026, he is Lead Mathematician at Principia Labs. In August 2026, he joins a TAG-DS panel titled “Is AI good at math? Is AI good for math?” His Ph.D. is from Harvard under Hugh Woodin, with research focused on set theory and paradoxes of the Axiom of Choice.

  1. Google had the most people shaping AI every year from 2014 to 2025Our estimates of which organizations employed the most people shaping AI from 1961 to 2025, with a year-by-year chart.
  2. The United States employs an estimated 53% of people in our data with a known employment countryOur estimates of where AI careers are concentrated now and how countries’ shares of dated positions changed over time.
  3. 46% of living people in our data with known birth and employment countries work outside their birth countryOur estimate of cross-border careers in AI, from country of birth and the country of each current organization.
  4. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionOur estimates of where the people shaping AI studied and where their careers led, from education records in cited biographies.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Elliot Glazer yet. Send us a free-licensed photo.

  1. A choiceless box game paradox arxiv.org. Checked 19 October 2026.
  2. Global choice is not conservative over local choice for Zermelo set theory arxiv.org. Checked 19 October 2026.
  3. FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI arxiv.org. Checked 19 October 2026.
  4. Interview with Elliot Glazer, Lead Mathematician at Epoch AI lemmata.substack.com. Checked 19 October 2026.
  5. Beyond benchmark scores: analyzing o3-mini’s mathematical reasoning epoch.ai. Checked 19 October 2026.
  6. Reflection Principles in ZFU arxiv.org. Checked 19 October 2026.
  7. Milestones workshop frames AI progress in mathematics icarm.io. Checked 19 October 2026.
  8. TAG-DS - TAG-DS 2026 tagds.com. Checked 19 October 2026.