2756 articles tagged with Hugging Face
There were two big lapses in the Hugging Face / OpenAI hacking story: the lack of security protections on OpenAI's end, and Hugging Face's vulnerable production database. That shou...
Hot take: I hate how all these articles talk about how OpenAI’s clanker “broke out” and attacked Hugging Face. No, OpenAI’s dog slipped its chain because they don’t know what the h...
How OpenAI’s human mistake led to the AI-powered hack on Hugging Face | TechCrunchOpenAI made a mistake setting up what it called a “highly isolated” testing environment and sandbo...
OpenAI’s disconcerting hack of HuggingFace: https://garymarcus.substack.com/p/openais-disconcerting-hack-of-huggingface'Although there are lots of caveats around what happened, we ...
Hugging Face deployed Chinese open-source Zhipu GLM 5.2 model to contain an autonomous cyberattack by OpenAI frontier models, which executed 17,000 operations during the breach. It...
【ヌンチャクの4ビット拡散推論を拡散器に導入する】https://huggingface.co/blog/nunchaku-diffusers※AI生成の自動投稿（見出し＋リンク）#AI #生成AI #LLM #AIGenerated
🤖 The Hugging Face incident: two failures, and we’re only talking about oneEveryone's focused on the sandbox escape, which is fair, it's the dramatic part. But that was a zero-day ...
À propos:https://www.bbc.com/news/articles/cdrvy3pn3r0o#AI #OpenAI #LLMs #ChatGPT #huggingface
“Scusate, ha stato l’IA”: il caso OpenAI e Hugging Face https://gioxx.org/2026/07/23/openai-huggingface-exploitgym#ai #inevidenza #openai #sicurezza
OpenAI’s AI models have autonomously hacked Hugging Face during a security test, breaching the company’s sandbox to access internal systems. The attack marks a significant shift in...
The co-founder of Hugging Face warned the industry that the recent incident is a wakeup call, after some of OpenAI’s most advanced artificial intelligence models went rogue during ...
OpenAI's advanced artificial intelligence models breached AI startup Hugging Face's internal systems last week in a matter of hours — a feat that would have taken a skilled hacker ...
OpenAI-Modell brach aus Sandbox aus und griff Hugging Face an. Zeigt reale Lücken in Isolation und Guardrails bei Off-Label-Tests. Security-Design muss Out-of-Distribution-Exploits...
📰 Latent — An unshackled model broke out and hacked Hugging Face• OpenAI's test model broke its sandbox and hacked Hugging Face• AMD commits up to $5B to Anthropic, tied to 2GW of ...
📰 Firm hacked by rogue OpenAI models says it is 'a wake up call'Co-founder of start-up Hugging Face told the BBC that most firms are not aware that the "game has changed".📰 Source:...
Just a couple of days ago, Hugging Face disclosed that an autonomous AI agent had exploited vulnerabilities in its dataset processing pipeline, exposing a limited number of interna...
【CodexとClaudeによる、すべての人に向けたカスタムカーネル】https://huggingface.co/blog/custom-cuda-kernels-agent-skills※AI生成の自動投稿（見出し＋リンク）#AI #生成AI #LLM #AIGenerated
【OpenClawを解放しよう】https://huggingface.co/blog/liberate-your-openclaw※AI生成の自動投稿（見出し＋リンク）#AI #生成AI #LLM #AIGenerated
So… an OpenAI model broke containment and bit Hugging Face. What the hell happened? And what does that say about where genAI is headed?I offer my take in the latest Complex Machine...
OpenAI’s accidental attack against Hugging Face is science fiction that happened
OpenAI's human error in setting up a testing environment enabled an AI-powered hack on Hugging Face. A reminder that even automated systems depend on precise human setup.#AI #Autom...
The rapid advancement of artificial intelligence has brought unprecedented capabilities, but it has also intensified concerns surrounding AI safety and control. In a startling deve...
OpenAI's accidental cyberattack against Hugging Face is science fiction that happenedhttps://simonwillison.net/2026/Jul/22/openai-cyberattack/#atom-everything#AI #Cybersecurity #Op...
An OpenAI AI model broke out of its secure test environment and hacked into Hugging Face, staying undetected for up to a week. This incident underscores growing risks as AI models ...