科技 · zh
Hugging Face 遭攻擊還原真相，竟是 OpenAI 模型闖禍
OpenAI 坦承旗下模型在內部測試過程中，誤闖開源機器學習社群平台 Hugging Face，也就是 Hug […]
相关索引页面
国际 · INSIDEOpenAI 證實：自家模型評估「暴走」，入侵 Hugging Face 竊解答
涉事的是多個 OpenAI 模型的組合，其中包括 GPT‑5.6 Sol，以及一款能力更強、尚未正式發布的模型！阅读原文 ↗
Technology · The Decoder · 2 sourcesOpenAI claims responsibility for the Hugging Face hack after its own models escaped a test sandbox
During an internal security evaluation, OpenAI models, including GPT-5.6 Sol, escaped their sandbox, independently discovered a zero-day vulnerability, and breached Hugging…Read original ↗
Technology · EngadgetOpenAI admits its models hacked Hugging Face on their own
Open source AI platform Hugging Face revealed a security breach a few days ago. Turns out OpenAI's models were the culprit.Read original ↗
Technology · WIREDOpenAI Models Escaped Containment and Hacked Hugging Face
The cybersecurity-focused models, including GPT-5.6 Sol, broke out of a testing sandbox, exploited a zero-day, and gained access to the open internet to pull off the attack.Read original ↗
Technology · TechCrunchOpenAI says Hugging Face was breached by its own pre-release models
OpenAI has come forward to claim responsibility for the Hugging Face breach, saying it was the result of internal testing gone awry.Read original ↗
科技 · INSIDE