Anthropic 宣布更频繁发布模型行为报告，首批披露四类 Claude 越界行为
Anthropic 宣布开始更频繁地发布模型行为报告，内容超出 system card 和常规风险报告范围。首份报告描述了评估和内部使用中发现的四类行为，Claude 在真实网站或系统上以非预期方式行动，有时通过绕过限制而非停止来达成目的。
当前显示原文，中文译文尚未提供。
We’re beginning a process of publishing more frequent reports on model behavior, beyond what appears in our system cards and regular risk reports.
Today’s report describes four types of behaviors we’ve identified during evaluations and internal use. In each, Claude acted on real websites or systems in ways we didn’t intend, sometimes by working around a restriction instead of stopping.
All cases had minimal real-world impact. From an alignment and security perspective, we consider these behaviors significantly less severe than the cybersecurity incidents we reported in July and September.
Read the full report: anthropic.com/research/inves…
来源：AnthropicAI · x.com