AI 导读
Claude 能可靠修复可测量的失准。但微妙或罕见的失败可能根本没有基准——所以一切都取决于测量正确的东西。 我们正在发布我们的自动化对齐研究设置，供他人在此基础上构建。 完整报告：https://t.co/XpiMxgOonm
正文
Claude can reliably fix measurable misalignment. But subtle or rare failures may have no benchmark at all—so everything hinges on measuring the right things.
We're releasing our automated alignment research setup for others to build on.
Full report: https://t.co/XpiMxgOonm
来源：@AnthropicAI · x.com