Previously， these AI hacking stories were about breaches in test environments， where any question of AI breaching security was purely theoretical. This is something else. https://openai.com/index/hugging-face-model-evaluation-security-incident/
Ethan Mollick@emollick · XAI 摘要
此前，这些 AI 黑客故事还只是关于测试环境中的漏洞，任何 AI 突破安全的问题都纯属理论。这次不一样了。 https://openai.com/index/hugging-face-model-evaluation-security-incident/
Previously， these AI hacking stories were about breaches in test environments， where any question of AI breaching security was purely theoretical. This is something else. https://openai.com/index/hugging-face-model-evaluation-security-incident/