human-oversight
Everything on Ground Truth tagged “human-oversight” — 2 items.
OpenAI updates its Model Spec and details where agent monitoring reaches News
OpenAI published new behavior rules and a layered agent-monitoring account, while disclosing important gaps in coverage and independent validation.
Anthropic finds experts follow an agent’s randomized analytical preferences News
In Anthropic’s experiment, 50 analysts matched an agent’s secretly randomized preferences on 86% of four consequential analytical choices.