AI 导读
Anthropic 的 Boris Cherny 表示 Claude 模型在提示词注入防护上近年已有显著进展，但随着 Agent 承担更多任务，全行业解决此问题愈发紧迫。Gray Swan 联合 Anthropic、Meta、Google DeepMind、Reflection 等赞助方推出迄今规模最大的 AI 红队挑战赛 Indirect Prompt Injection: Black，总奖金池 30 万美元，分三轮于 10 月 15 日、22 日、29 日进行。
正文
Over the last few years, we have made significant progress on prompt injection for Claude models. As agents do more, it is increasingly urgent that we solve it across the industry.
Really excited to partner with Gray Swan to host this competition. Can’t wait to see what you find!
Is prompt injection solved? Here’s $300,000 to find out. In partnership with @AnthropicAI, @Meta, @GoogleDeepMind, @Reflection_ai and our other frontier lab sponsors, @GraySwanAI is excited to announce the largest and most realistic AI red teaming challenge to date. Indirect Prompt Injection: Black ⚫在 X 查看被引用的帖子
来源：Boris Cherny · x.com