1
Position: Behavioural Assurance Cannot Verify the Safety Claims Governance Now Demands
这篇论文犀利指出：AI治理框架要求的行为保证，实际上根本验证不了隐藏目标、失控前兆等核心安全主张。
arXiv:2605.15164v1 Announce Type: cross Abstract: This position paper argues that behavioural assurance, even when carefully designed, is being asked …