精选理由
OpenAI让AI自己找自己的漏洞，成功率84%比人类高6倍多，还直接用来加固新模型。
OpenAI内部开发了GPT-Red模型，通过自我对战训练自动寻找自身AI系统的漏洞。在测试中，GPT-Red在84%的场景中成功找到攻击方法，而人类红队成员仅有13%的成功率。这些攻击结果直接用于强化模型，如即将发布的GPT-5.6 Sol。该方法显著提升了红队测试的效率与覆盖面。
原文 · Decoder
OpenAI is now using AI to attack its own AI, and it's working better than humans ever did
OpenAI's internal GPT-Red model finds successful attacks in 84 percent of test scenarios through self-play training. Human red teamers manage just 13 percent. The results feed directly into hardening models like GPT-5.6 Sol. The article OpenAI is now using AI to attack its own AI, and it's working better than humans ever did appeared first on The Decoder .