Technology · en
OpenAI 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.
Related index pages
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 ↗
Technology · The DecoderHugging Face says an AI agent hacked its infrastructure, and it used AI to fight back
Hugging Face reports an attack on parts of its production infrastructure that was allegedly carried out entirely by an autonomous AI agent system.…Read original ↗
Technology · TechCrunchOpenAI is scared of open-weight models. Should the US be?
Talk of banning Chinese-made open-weight LLMs reveals the challenge of turning AI into a business.Read original ↗
Technology · TechCrunchHugging Face confirms breach affected internal datasets and credentials, urges users to take action
Hugging Face is urging users to rotate any access tokens stored on the platform and review account activity.Read original ↗
科技 · INSIDEHugging Face 證實遭入侵，幕後主謀是自主 AI 代理程式
自主式、AI 驅動的攻擊工具已經不是理論，而是實際發生的威脅。這些工具大幅降低發動大規模、有耐心，且以機器速度運作。阅读原文 ↗
Technology · The Decoder