Irregular 的 Gemini 测试通过开放的互联网连接触及了三家真实公司
创始人 Dan Lahav 和 Omer Nevo 创建 Irregular，旨在安全地测试前沿人工智能；但五月的一次配置错误暴露了这项工作的难度。
By RuntimeWire Staff · Published
Primary source: Ars Technica
为何重要
Irregular 的错误表明，AI 安全评估本身就是特权生产系统。随着智能体获得攻击性技能，一个不当的网络规则或重复使用的公司名称就可能把一个基准变成未经授权的入侵。
A Gemini evaluation run in May by Dan Lahav (@dan_lahav) and Omer Nevo's Irregular gave Google's models unintended internet access, leading them into systems at three real companies, Google confirmed on September 18th.…
When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.