Skip to main content

    Peter Henderson

    Assistant Professor of Computer Science and School of Public and International Affairs at Princeton University, works at the intersection of ML evaluation, AI safety, and real-world deployment, contributor to the 2026 HAL reliability research.

    #71 AI Evaluation
    17CiteRank

    Last updated 11 Nov 2026 · Named in 4 answers across 3 engines
    Bing AI Mode starts a separate baseline. Copilot remains a separate public engine and keeps its history; changes across the switch are not like-for-like growth.

    How AI engines see them

    Recognized by 5 of 5 measured engines. Updated 2026-09-19
    • ChatGPTNot named

      Contributes to Holistic Evaluation of Language Models (HELM)

    • GeminiNot named

      Leads the Polaris Lab and works on AI evaluation benchmarks

    • Google AI ModeNot named

      Contributes to AI safety and machine learning evaluation

    • PerplexityNot named

      Emphasizes caution in AI evaluation and real-world readiness

    • Bing AI ModeNot named

      No description yet.

    • CopilotNot named

      Pushes beyond traditional accuracy-focused metrics

    Top Segments

    • #71AI Evaluationof 100
      Named in 1 answers

    Track Peter

    Follow Peter's measured AI visibility and see the questions where they rank.