OpenAI说新模型Astra在网络安全上风险最高，他们准备加码防护再上线，还把能力给防御者用。
OpenAI宣布，即将推出的模型Astra被其Preparedness Framework评估为首个“关键”级网络安全模型。这一分级意味着Astra在自主网络攻击等能力上达到该框架的最高风险等级。OpenAI表示已针对这一场景预先制定计划，并将在Astra后续开发中实施额外安全管控。该公司正努力让Astra广泛可用，以将其高级网络防御能力提供给防御者。
After evaluating one of our upcoming models, Astra, we're treating it as our first "critical" model ...
After evaluating one of our upcoming models, Astra, we're treating it as our first "critical" model for cybersecurity under our Preparedness Framework. This is a scenario we've planned for, and we're putting additional controls in place to ensure Astra's further development happens safely and securely. We're working hard to make Astra broadly available, and get its advanced cyber capabilities into the hands of defenders. openai.com/index/respondi… 💬 181 🔄 103 ❤️ 1153 👀 64983 📊 265 ⚡