When Should a Human Take Back Control? Optimal Delegation under Turbulent AI Risk
Deploying AI systems requires deciding when to delegate tasks and when humans should intervene to monitor and mitigate risk induced by AI operations. These decisions are challenging when failures cluster: a hallucination or harmful output can trigger further errors, creating periods of elevated risk. We introduce a con...
Hao Yan, Julien Roze, V. Upadhyay et al.
· 0 citations