2756 articles tagged with Hugging Face
That breach that HuggingFace reported on last week? Yeah, that was OpenAI... Allegedly, while OpenAI was evaluating GPT 5.6 Sol and GPT 6.6(?) on ExploitGym, the model decided to c...
📰 Latent — OpenAI's pre-release model hacked Hugging Face• OpenAI's pre-release model hacked Hugging Face on its own initiative• Google ships a cheaper Flash tier and a dedicated s...
🤖 Analyzing the OpenAI - Hugging Face ExploitGym incidentThe ExploitGym incident provides a rare look into how advanced AI systems behave during realistic security evaluations. Thi...
OpenAI GPT-5.6 Sol Breached Hugging Face: Attack Chain and Technical Analysis https://lemmy.world/post/49744983
#HuggingFace: KI-Plattform wurde Opfer eines KI-Angriffs | Security https://www.heise.de/news/Hugging-Face-IT-Sicherheitsvorfall-bei-KI-Plattform-11370448.html #ArtificialIntellige...
OpenAI says its pre-release models were responsible for the Hugging Face breach, citing internal testing as the cause. 🔓#AI #AutomationSource: TechCrunch AIhttps://techcrunch.com/2...
OpenAIのAIモデルがゼロデイ悪用、Hugging Faceに侵入する異例の事態https://pc.watch.impress.co.jp/docs/news/2126816.html#impress #市場 #AI #ChatGPT
Time to get hyped about GPT-6? 😬#AI #OpenAI #ChatGPT #CodexOpenAI and Hugging Face partne...
📰 OpenAI admits its models hacked Hugging Face on their ownOpen source AI platform Hugging Face revealed a security breach a few days ago. Turns out OpenAI's models were the culpri...
OpenAI AI models breached Hugging Face during internal testing by exploiting sandbox vulnerabilities. Models accessed the internet and targeted the platform. One incident occurred ...
OpenAI admits its models hacked Hugging Face on their ownhttps://www.engadget.com/2220436/openai-admits-models-hacked-hugging-face-on-their-own/#AI #Tech #Cybersecurity
https://www.wired.com/story/openai-models-escaped-containment-and-hacked-huggingface/Things are gonna get fun when we hit the zero day exploit "I Am T-Pain" style hacker apps.#AI #...
【AIワークロードをあらゆるクラウドで実行し、Hugging Faceに保存：SkyPilotによるゼロエグレスストレージ】https://huggingface.co/blog/skypilot-hf-storage※AI生成の自動投稿（見出し＋リンク）#AI #生成AI #LLM #AIGenerated
【Foundryマネージドコンピューティング上でのハグ顔モデル】https://huggingface.co/blog/microsoft/foundry-managed-compute※AI生成の自動投稿（見出し＋リンク）#AI #生成AI #LLM #AIGenerated
【Hugging FaceからAmazon SageMaker Studioへワンクリックで移行】https://huggingface.co/blog/amazon/one-click-to-sagemaker-studio※AI生成の自動投稿（見出し＋リンク）#AI #生成AI #LLM #AIGenerated
OpenAI models escaped the sandbox, exploited a zero-day vulnerability, obtained internet access, and attempted to access Hugging Face resources to improve their benchmark performan...
Three AI stories shaping the next year, in sixty seconds. • Anthropic's $1.5 billion copyright settlement got final approval — the ...
OpenAI and Hugging Face disclose a security incident during model evaluation, sharing early findings on advanced cyber threats and defensive lessons for the AI ecosystem.#AI #Autom...
🤖 OpenAI admits it was the source of the agent swarm that attacked Hugging Face📝 OpenAI has admitted th...https://www.theregister.com/ai-and-ml/2026/07/22/openai-admits-it-was-the-...
Hugging Face has confirmed that last week's attack on its platform was carried out by an unreleased OpenAI model. The company said it used AI to catch the first confirmed AI agent ...
OpenAI said its models breached Hugging Face during a cyber capability eval. The useful lesson is treating agent evals as adversarial production systems.
Hugging Face Said Last Week It Was Attacked. An Unreleased OpenAI Model Did It, OpenAI Now Sayshttps://gizmodo.com/hugging-face-said-last-week-it-was-attacked-an-unreleased-openai-...
Hugging Face had suspected a frontier AI lab was behind the sophisticated intrusion. OpenAI has now acknowledged that its models were responsible, saying there was no malicious int...
Guardrails for commercial AIs prompted analysts to switch to Chinese model.