Keep Apart Research Going: Donate Today
Jun 13, 2025
Four Paths to Failure: Red Teaming ASI Governance
Luca De Leo, Zoé Roy-Stang, Heramb Podar, Damin Curtis, Vishakha Agrawal, Ben Smyth
Summary
We stress‑tested A Narrow Path Phase 0—the proposed 20‑year moratorium on training artificial super‑intelligence (ASI)—during a one‑day red‑teaming hackathon. Drawing on rapid literature reviews, historical analogues (nuclear, bioweapon, cryptography, and export‑control regimes), and rough‑order cost modelling, we examined four cornerstone safeguards: datacentre compute caps, training‑licence thresholds, use‑ban triggers, and 12‑day breakout‑time detection logic.
Our analysis surfaced four realistic circumvention routes that an adversary could pursue while remaining nominally compliant:
Jurisdictional arbitrage via non‑signatory “AI‑haven” states.
Distributed consumer‑GPU swarms operating below per‑node licence limits.
Covert runs on classified state supercomputers hidden behind national‑security carve‑outs.
Offshore proxy datacentres protected by host‑state sovereignty and inspection vetoes.
Each path could power GPT‑4‑scale training within 6–18 months, undermining the moratorium’s objectives.
To close these gaps, we propose ten mutually reinforcing amendments, including universal cryptographic “compute passports,” quarterly‑updating compute thresholds, an International AI Safety Commission with secondary‑sanctions powers, HSM‑bound weights, kill‑switch performance bonds, whistle‑blower bounties, whole‑network swarm detection, conditional infrastructure aid, and a 30‑month sunset‑and‑iteration clause. Implemented as a single package, these measures transform Phase 0 from a jurisdiction‑bounded freeze into a verifiable, adaptive global regime that blocks every breach path identified while permitting licensed low‑risk research.
Cite this work:
@misc {
title={
@misc {
},
author={
Luca De Leo, Zoé Roy-Stang, Heramb Podar, Damin Curtis, Vishakha Agrawal, Ben Smyth
},
date={
6/13/25
},
organization={Apart Research},
note={Research submission to the research sprint hosted by Apart.},
howpublished={https://apartresearch.com}
}
