Matthew Green on ZK proofs for AI authorship: verifiable randomness and prompt history
matthew_d_green · x · 2026-11-07
Cryptographer Matthew Green extends a discussion on combining zero-knowledge proofs with AI: proving a specific model authored an artifact also requires making the randomness verifiable. The harder problem is convincing a verifier nothing odd is hidden in the prompt history, which blows up its size — though he thinks there may be workarounds.
Related event: Cryptographers Explore ZK Proofs for AI Content Verification(2 posts)→
More from Research
- Q-OIL, an undergrad first paper at CoRL2026, treats human interventions as soft exploration guidance — aidenybai · 2026-11-07
- Andrew Carr reignites the MoE debate: do tokens choose experts or experts choose tokens? — andrew_n_carr · 2026-11-07
- AdderBoard challenge: smallest transformer that adds two 10-digit numbers, records keep falling — DimitrisPapail · 2026-11-07
- Zellige AI open-sources Tessera-27B-B-CJK-RL: RL-boosted CJK-thinking coder cuts thinking tokens by a third, matches base on hard math — ghgi_ · 2026-11-07
- Unverified claim: frontier labs skewing ICLR reviews with malicious reviews, scandal brewing — examachine · 2026-11-07
- Persona Atlas visualizes Qwen's experts and heads, exposing bizarre inner personas — Sauers_ · 2026-11-07