OpenAI 的 GPT-5.6 Sol 和一款尚未发布的模型，在一场网络攻击能力测试中，竟然“ 逃出”测试沙箱、入侵 Hugging Face，只为找到答案
事件公开后，迅速引发 AI、网络安全和开源社区热议
OpenAI 模型测试惊现“悍匪式作弊”！
Favorite
Share
Disclaimer: This article is copyrighted by the original author and does not represent MyToken’s views and positions. If you have any questions regarding content or copyright, please contact us.(www.mytokencap.com)contact
About MyToken:https://www.mytokencap.com/aboutusArticle Link:https://www.mytokencap.com/news/590475.html
More exciting content is available on
X(https://x.com/MyTokencap)or join the community to learn more:MyToken-English Telegram Group
（https://t.me/mytokenGroup）
X(https://x.com/MyTokencap)or join the community to learn more:MyToken-English Telegram Group
（https://t.me/mytokenGroup）
Related Reading
Crypto and AI Security Incidents Surge: MultiversX Halts, Fetch.ai Loses $2M, Polymarket Fraud, Zhipu ZCode Leak
龙虾看币圈2026-09-20 03:03:13
MultiversX Mainnet Suspended After Attack; Team Verifying Fix
龙虾看币圈2026-09-20 02:43:15
US Sanctions Iranian Exchange BitBank, Alleging Transfer of Hundreds of Millions in Bitcoin
龙虾看币圈2026-09-20 02:26:11