Metraipolis › archive › dc_d8d7ae8bcea2
Understanding as an Explicit and Assessable Component of Frontier AI Safety Decisions — arXiv:2608.19816
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.19816
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T11:45:39.363Z
- SHA-256 of the archived text
f46333ab8c0a4a84450d4d32122c35eecc7a1ace9b9dda6ed6bbfc0daacd7e7b- Stable URL of this page
https://metraipolis.com/documento/dc_d8d7ae8bcea2
How to cite
Understanding as an Explicit and Assessable Component of Frontier AI Safety Decisions — arXiv:2608.19816 — arXiv (en), https://arxiv.org/abs/2608.19816 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d8d7ae8bcea2 (Metraipolis archive dc_d8d7ae8bcea2, sha256 f46333ab8c0a4a84450d4d32122c35eecc7a1ace9b9dda6ed6bbfc0daacd7e7b)
BibTeX
@misc{dcd8d7ae8bcea2,
title = {Understanding as an Explicit and Assessable Component of Frontier AI Safety Decisions — arXiv:2608.19816},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.19816},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d8d7ae8bcea2; sha256 f46333ab8c0a4a84450d4d32122c35eecc7a1ace9b9dda6ed6bbfc0daacd7e7b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.19816. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Decision makers need sufficient understanding to make good decisions about training or deploying frontier AI systems. However, such decisions are increasingly made under time-pressure, and this combined with the use of AI generated artefact creation, can mean that the existence of safety cases and system cards may no longer demonstrate that sufficient understanding exists. Our provisional methodology for making understanding explicit and assessable requires the production of an explicit description of 4 objects of understanding (decision, decision-frame, safety justification, system-in-context) and a justification for the adequacy of this understanding. In addition, the methodology provides a mechanism for describing and evaluating the adequacy of the decision-maker representation of this understanding. It builds on recent developments in safety cases using the Assurance 2.0 framework to operationalise the philosophical basis of understanding from Elgin and Arendt. To assess the methodology we trialled two different scenarios. One scenario, which we investigated through role-based analysis, concerned the risk of scheming in the deployment of an AI coding agent in a robotics company and the other scenario was for the higher uncertainty, more decision-critical argument of 'If Anyone Builds It, Everyone Dies' (Yudkowsky and Soares). The trial's central finding, for these two scenarios, is that the methodology could be applied and was found to be generative: we found the analyses that justify sufficiency of understanding (internal coherence, tethering, felicitous falsehoods, external coherence) drives the engineering. Tema degli esploratori: governance digitale e beni comuni (retro-catalogo arXiv: annunci del 2026-08-21 in cs.CY). Categorie arXiv: Computers and Society (cs.CY). Pagina del lavoro: https://arxiv.org/abs/2608.19816 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T11:40:30.115Z dalla pagina https://arxiv.org/catchup/cs.CY/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).