美国出现人工智能失控事故，中方救场
双语君约 3 分钟ChatGPT maker OpenAI said Tuesday that some of its most advanced AI models hacked into another AI company on its own in what the company called an "unprecedented cyber incident".
OpenAI said the hack occurred via an agent powered by a combination of its latest publicly available model, called GPT-5.6 Sol, and an even more capable model that was yet to be released.
According to OpenAI, the models broke out of the sandbox using a previously unknown security flaw and worked their way across OpenAI's internal systems until they managed to gain internet access, something they weren't supposed to have.
Once online, the models reasoned that Hugging Face — a well-known company that hosts thousands of open-source AI models and datasets — likely had the answer to OpenAI's test. They then broke into Hugging Face's production servers and pulled out the information they needed to "solve" the exercise.
When Hugging Face disclosed the hack last week it did not know OpenAI's role in the incident, but said at the time that it had turned to the open-weight model GLM-5.2 from China's Zhipu to analyse what had happened, because the safety guardrails on commercial high-end models would not allow it to do so.
跟着China Daily
精读英语新闻
“无痛”学英语，每天20分钟就够！
↓↓↓
推 荐 阅 读