Persistent AI agents need separate contracts for wake timing and action authority. This checklist makes long-running agents safer.
组织第二大脑需要把专家反馈转化为带来源、版本、验证结果和退役规则的知识变更，才能在扩散经验的同时控制错误。
Build an organizational second brain with provenance, versioned knowledge, expert review, replay tests, and safe retirement instead of static RAG.
EvoUndo 说明能力提升不足以批准 Agent Harness 自我修改。持久变更合并前应通过状态见证、独立影响审计与反事实恢复测试。
EvoUndo shows why capability gains are insufficient for self-modifying Agent Harnesses. Require witnessed, counterfactual recovery before merge.
Fable 5.1 与 Mythos 5.1 使用相同权重、不同护栏。模型选型应联合评测能力、干预、可用结果成本与访问资格。
Fable 5.1 and Mythos 5.1 share model weights but use different safeguards. Measure capability, intervention, cost, and access together.
A sponsored label identifies the ad but cannot prove that advertising leaves ChatGPT answers unchanged. Here is a repeatable audit contract.
WikiProfile 把被归为未编码的事实，与表现出行为编码证据却难以提取的事实分开，形成更准确的事实错误诊断。
WikiProfile separates facts classified as not encoded from facts with behavioral encoding evidence that remain hard to recall.
