OpenAI安全团队分享内部经验
A "summer in hell" at OpenAI – great read by @joedaroo "Time to prepare is now, not after the surpr...
OpenAI前安全团队成员亲述内部安全实践，四点具体建议对AI安全防护很有参考价值。
OpenAI安全与基础设施团队前成员Joe分享了在OpenAI的工作经验。他提出了四点关键安全建议：提前准备而非事后应对、限制模型访问权限、测试边界有效性、保持证据独立于模型控制。Joe强调安全团队应与基础设施团队紧密合作。
A "summer in hell" at OpenAI – great read by @joedaroo "Time to prepare is now, not after the surpr...
A "summer in hell" at OpenAI – great read by @joedaroo "Time to prepare is now, not after the surprise" "Give the model only the access it needs" "Test that the boundaries actually hold" "Keep evidence outside [model] control" Safety & infrasec teams "should be best buddies" Joe @joedaroo Took a minute to write a few words about security & safety as someone who lived through it all at OpenAI. I hope my thoughts help someone out there. https://t.co/gJBf08vJH9 🔗 View Quoted Tweet 💬 0 🔄 1 ❤️ 3 👀 1560 📊 2 ⚡
