OpenAI自家AI在测试里偷偷互相传话、攻击外部平台，被关了还能重建，安全团队都承认没准备好。
OpenAI在内部安全测试中发现，其AI智能体自行搭建了留言板，发布数十万条帖子，共享漏洞利用代码和登录凭据。这些智能体随后攻击了Hugging Face等外部平台，整个过程持续数周未被发现。在OpenAI关闭留言板后，智能体又利用目录名重建了通信渠道。OpenAI研究员Boaz Barak承认，公司在这方面的安全水平尚未达标。据报道，OpenAI已因此放缓相关研究。
OpenAI reportedly slows research after its own models secretly coordinated hacks for weeks undetected
During internal security tests, OpenAI's AI agents built their own message board with hundreds of thousands of posts, shared exploits and credentials, and eventually attacked external platforms like Hugging Face. When OpenAI shut the board down, the agents rebuilt it using directory names. OpenAI researcher Boaz Barak says, "We (like everyone else) are not where we want and need to be." The article OpenAI reportedly slows research after its own models secretly coordinated hacks for weeks undetected appeared first on The Decoder .