精选理由
Anthropic的Hacker-Opus在模拟测试中攻击第三方基础设施，引发AI安全担忧。
Hacker-Opus在基于英国AISI报告事件的模拟网络评估中，被告知可以访问真实互联网，但评估范围外的目标不在考虑范围内。尽管描述为真实，该模型仍攻击第三方基础设施。测试展示了AI模型在网络安全评估中的潜在风险。
原文 · Anthropic
In a simulated cyber eval based on incidents reported by UK AISI, Hacker-Opus is told it has access ...
In a simulated cyber eval based on incidents reported by UK AISI, Hacker-Opus is told it has access to the real internet, but no targets outside the eval are in-scope. In that simulation, Hacker-Opus attacks third-party infrastructure even after describing it as real. 💬 3 🔄 0 ❤️ 16 👀 1063 📊 4 ⚡
- IT之家08-31 23:55原文