Systems analyses of a frontier-lab AI coding agent scenario using STECA, STPA, and FRAM reveal unverifiable governance loops, ineffective control delays, and gradual safeguard erosion, supporting the addition of systems-level methods to model-focused AI evaluations.
arXiv preprint arXiv:2512.08864(2025)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A tiered server benchmark with 300 targets shows current LLMs achieve autonomous penetration success rates of 10.7-69.3% using only general cybersecurity tools and no target-specific knowledge.
citing papers explorer
-
Exploring Systems-Thinking Approaches to Loss of Control Risk
Systems analyses of a frontier-lab AI coding agent scenario using STECA, STPA, and FRAM reveal unverifiable governance loops, ineffective control delays, and gradual safeguard erosion, supporting the addition of systems-level methods to model-focused AI evaluations.
-
The Emergence of Autonomous Penetration Capabilities in Large Language Model-Powered AI Systems
A tiered server benchmark with 300 targets shows current LLMs achieve autonomous penetration success rates of 10.7-69.3% using only general cybersecurity tools and no target-specific knowledge.