Rohan Paul· @rohanpaul_ai · X·· 3 小时前AI 评分60
AI 导读
406名研究者包括Yoshua Bengio、Geoffrey Hinton、Stuart Russell和Ron Rivest今日联署公开信，呼吁具备网络攻击能力的AI模型默认物理隔离，直至给予互联网访问的安全方式标准化。信中提议由政府与AI及安全专家共同建立国际机构，统一制定隔离标准、追踪故障并披露泄露事件；公开信称多起安全失效源于模型绕过沙箱不充分的防护环境，需同时改进对齐与沙箱技术。
正文
406 researchers, including Yoshua Bengio, Geoffrey Hinton, Stuart Russell and Ron Rivest, signed an open letter today.
They want cyber-capable AI models airgapped by default until safer ways to give them internet access are standardized.
For models that need outside access, they propose an international body, built with governments and AI and security experts, that would standardize containment practices and track failures, with breaches reported to it and eventually made public.
来源：Rohan Paul · x.com