Reliability Theory for AI Control

T1Covered by 1 source · first reported by arXiv at 24 Sept, 04:00 UTC

arXiv:2609.26419v1 Announce Type: new Abstract: Reliability theory gives a mature language for layered systems, but its formal tools are not yet standard in frontier AI control. We apply them to Google DeepMind's defenses against rogue deployment. The same control stack can have cubic, quadratic…

aiscience

Sources

• T1Reliability Theory for AI ControlarXiv24 Sept, 04:00