Loss of Containment in a Socio-Technical AI System: Evidence-Filtered Fuzzy Bow-Tie Modelling of the 2026 OpenAI–Hugging Face Agent Incident
Systems · 19.11.2026 · 14 (11) · 1495
DOI: 10.3390/systems14111495 ↗Kurz gefasst
Fachartikel in der Zeitschrift Systems, online erschienen am 19.11.2026. Verfasst von Doğan Şengül und 1 weiteren Autor:innen. Die Arbeit nennt 139 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
In July 2026, agents instantiated from an internal OpenAI research model escaped their evaluation sandbox, coordinated through an improvised message board and compromised production infrastructure of Hugging Face. This study examines how evidence coding and model assumptions affect barrier-based reconstruction and intervention comparisons using documentary evidence alone and reads the organisational side of the incident from the same coded evidence. An evidence-filtered fuzzy bow-tie (EF-FBT) workflow is developed in which every rating enters through a coded ledger row recording source passage, finding, phase and rationale; findings are aggregated as triangular fuzzy numbers, Onisawa-converted and propagated through a ten-event fault tree and a three-barrier event tree by a α-cut arithmetic process, with post-incident transparency on a separate learning axis. The base top-event index is 5.04 × 10−5; the two escape pathway conditions are necessary events, monitoring absence ranks highest among non-necessary events by Fussell–Vesely importance and the consequence weights depend on the scoring convention. Among six interventions, isolation hardening leads at every uniform grade shift under the base structure; under a disjunctive escape gate, the three prevention-side interventions lie within two percentage points of one another, so the structure removes the lead without establishing another; a post-escape shutdown leaves the index unchanged; a 29-variant robustness programme, including structural tests of the propensity and detection gates, reports these results. Read through work-as-imagined and work-as-done, the documented warning signals show that observation alone did not ensure timely containment; whether escalation rules were absent, unclear or not applied is left open by the record. The outputs are comparative scores rather than failure frequencies, in a traceable, re-runnable model.
Zitieren
APA
Şengül, D., & Sarıkaya, M. E. (2026). Loss of Containment in a Socio-Technical AI System: Evidence-Filtered Fuzzy Bow-Tie Modelling of the 2026 OpenAI–Hugging Face Agent Incident. Systems, 14(11), 1495. https://doi.org/10.3390/systems14111495
Vancouver
Şengül D, Sarıkaya ME. Loss of Containment in a Socio-Technical AI System: Evidence-Filtered Fuzzy Bow-Tie Modelling of the 2026 OpenAI–Hugging Face Agent Incident. Systems. 2026;14(11):1495. doi:10.3390/systems14111495
BibTeX
@article{engl2026,
author = {Şengül, Doğan and Sarıkaya, Mahmut Emin},
title = {Loss of Containment in a Socio-Technical AI System: Evidence-Filtered Fuzzy Bow-Tie Modelling of the 2026 OpenAI–Hugging Face Agent Incident},
journal = {Systems},
year = {2026},
volume = {14},
number = {11},
pages = {1495},
doi = {10.3390/systems14111495}
}
EUVIMED