AGI Strategies

person

Tatsunori Hashimoto

Stanford; CRFM; LLM evaluation and security

Stanford assistant professor in CS and statistics. Member of the Center for Research on Foundation Models. Researches generalization and security properties of large models.

current Assistant Professor of CS and Statistics, Stanford University; Member, Stanford CRFM

Strategy positions

Evals-drivenendorses

Capability/risk evals gate deployment; evals are the load-bearing artefact

Argues robust evaluation requires carefully constructed datasets that resist contamination and reveal real generalization, not leaderboard-fitted numbers.

The dominant evaluation paradigm in NLP is fundamentally susceptible to contamination and overfitting. We need to design tests that are robust to the way models actually develop.
articleTatsunori Hashimoto, Stanford· Stanford CS· 2023· faithful paraphrase

Closest strategy neighbours

by jaccard overlap

Other people whose strategy tags overlap with Tatsunori Hashimoto's. Overlap is on tag identity, not stance; opposites can show up if they reference the same tags.

  • Aleksander Mądry

    shared 1 · J=1.00

    MIT; ex-OpenAI head of preparedness

  • Alex Meinke

    Alex Meinke

    shared 1 · J=1.00

    Apollo Research; deceptive alignment evaluations

  • Ali Rahimi

    Ali Rahimi

    shared 1 · J=1.00

    Google Brain ML researcher; 'Alchemy' speech

  • Anna Rogers

    Anna Rogers

    shared 1 · J=1.00

    IT University of Copenhagen; LLM benchmarking critique

  • Arati Prabhakar

    Arati Prabhakar

    shared 1 · J=1.00

    White House OSTP director (2022–2025)

  • Beth Barnes

    Beth Barnes

    shared 1 · J=1.00

    Founder of METR; dangerous capability evaluations

Record last updated 2026-04-25.