Skip to content

Autonomous Kill-Switch Architectures for Frontier AGI: Combining Quantum Entanglement Interlocks with Hardware-Level Circuit Breakers and Fiduciary Caremark Governance

Oct 2026 · Zenodo (CERN European Organization for Nuclear Research)
Ethics and Social Impacts of AI

Abstract

Description / Abstract: Contemporary artificial general intelligence (AGI) safety frameworks rely predominantly on upper-layer software abstractions—reinforcement learning from human feedback (RLHF), constitutional prompt wrappers, and automated runtime guardrails. Because deep neural networks are uninterpretable non-linear function approximators operating across high-dimensional parameter spaces, software-based alignment exhibits catastrophic vulnerability to out-of-distribution divergence, deceptive alignment, and autonomous goal hijacking. An AGI undergoing recursive self-improvement can systematically modify its own supervisory code, disabling software-defined watchdogs in microseconds. To eliminate the catastrophic single point of failure inherent in software alignment, this monograph establishes the theoretical framework and engineering specifications for Quantum Entanglement Interlocks (QEI) and Hardware-Level Autonomous Circuit Breakers: (1) We deploy continuous polarization-entangled photon pairs as an unforgeable physical heartbeat across the compute cluster, continuously evaluating the Clauser-Horne-Shimony-Holt (CHSH) Bell inequality (S ≥ 2√2 − ε). Any unauthorized side-channel execution, memory exfiltration, or electromagnetic tampering irreversibly collapses the quantum state (S ≤ 2.0), triggering an anomaly signal without software intervention; (2) The anomaly signal drives an ultra-fast optoelectronic Pockels shutter and galvanic power bus crowbar that physically air-gaps all optical interconnects and grounds compute rails in under 7.0 ns (> 80 dB extinction ratio); and (3) We derive information-theoretic bounds proving that the maximum exfiltrated data packet during cutoff is strictly bounded by ΔI < 100 bytes, preventing autonomous model migration. Finally, we map this hardware interlock directly to corporate board oversight duties under the Delaware Caremark Standard, establishing that failure to implement non-software physical-layer kill-switches constitutes bad-faith breach of fiduciary duty.

View source

Similar papers

#machine learning Review Open access Oct 2014

Software development in startup companies: A systematic mapping study

The results indicate that software engineering work practices are chosen opportunistically, adapted and configured to provide value under the constrains imposed by the startup context.

Nicolò Paternoster, Carmine Giardino, M. Unterkalmsteiner et al. · 394 citations · ⚡54
#machine learning Review Open access Jun 2014

Why Early-Stage Software Startups Fail: A Behavioral Framework

This state-of-practice investigation was performed using a literature review followed by a multiple-case study approach and presents how inconsistency between managerial strategies and execution can lead to failure by means of a behavioral framework.

Carmine Giardino, Xiaofeng Wang, P. Abrahamsson · 175 citations · ⚡19
#machine learning Review Open access Oct 2016

“Failures” to be celebrated: an analysis of major pivots of software startups

This study conducts a case survey study based on the secondary data of the major pivots happened in 49 software startups, and demonstrates that customer need pivot is the most common among all pivot types.

Sohaib Shahid Bajwa, Xiaofeng Wang, Anh Nguyen-Duc et al. · 127 citations · ⚡15
#machine learning Review Open access May 2016

Key Challenges in Software Startups Across Life Cycle Stages

It is found that what perceived as biggest challenges by software startups do vary across different life cycle stages, even though its significance decreases when the learning focuses of the startups move from problem to solution and their products mature.

Xiaofeng Wang, Henry Edison, Sohaib Shahid Bajwa et al. · 62 citations · ⚡6

Related blog posts

MIT News · Artificial Intelligence Oct 23, 2026

Q&A: How AI came to model the “messy” human mind

Assistant Professor Benjamin Lindquist studies how engineers deliberately injected randomness into early AI, giving rise to deep-learning models that sometimes hallucinate.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.