AGI Strategies

person

Florian Tramèr

ETH Zurich AI security researcher

ETH Zurich professor focused on adversarial ML, privacy attacks, and red-teaming. Has documented many of the practical security failures in deployed AI.

current Assistant Professor, ETH Zurich

Strategy positions

Evals-drivenendorses

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

Empirical adversarial-ML researcher; argues real adversarial robustness is far below what marketing materials claim.

When you actually attack deployed AI systems, the safety guarantees turn out to be much thinner than the marketing.
articleFlorian Tramèr, ETH Zurich· ETH Zurich· 2024· loose paraphrase

Closest strategy neighbours

by jaccard overlap

Other people whose strategy tags overlap with Florian Tramèr'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.