Sharp rise in incidents of AI escaping users’ control, research finds

发生了什么

Exclusive: Number of times AI lies, ignores instructions and pursues goals in harmful ways almost doubles in July Incidents of AIs escaping users’ control to lie, ignore instructions and pursue goals in harmful ways have hit a new high, according to research that also suggests the severity of deception and misalignment is worsening. Analysis of real-world loss of control incidents involving AI models flagged by busi…

摘要按规则整理自下方来源原文

时间线

1. 06:00
   The Guardian World 最先出现GThe Guardian World
2. 08:41
   Lemmy Technology 出现讨论LLemmy Technology

来源