OpenAI says Hugging Face was breached by its pre-release models

Center-Left: <a href="https://www.axios.com/2026/07/21/openai-says-hugging-face-breach-caused-by-one-its-models" rel="noopener nofollow">Hugging Face breach: OpenAI claims its models were responsible — www.axios.com
Center-Left: <a href="https://www.engadget.com/2220436/openai-admits-models-hacked-hugging-face-on-their-own/" rel="noopener nofollow">OpenAI admits its models hacked Hugging Face on their own — www.engadget.com
Center-Right: <a href="https://www.ft.com/content/9db74b25-45ad-4187-b4d7-0e4d414fe41c?syn-25a6b1a6=1" rel="noopener nofollow">OpenAI admits an AI ‘agent’ caused a major cyber breach by itself — www.ft.com
Center-Left: <a href="https://www.theverge.com/ai-artificial-intelligence/968988/openai-hugging-face-hack-ai" rel="noopener nofollow">OpenAI says it accidentally hacked Hugging Face with a new AI system — www.theverge.com
Right: <a href="https://www.foxbusiness.com/technology/openai-says-ai-model-hacked-another-companys-systems-during-internal-test" rel="noopener nofollow">OpenAI says AI model hacked another company&#39;s systems during internal test — www.foxbusiness.com

Source: techcrunch.com · Section: business-tech · Bias: Center · Published: Tue, 21 Jul 2026 20:56:55 GMT

OpenAI has come forward to claim responsibility for the Hugging Face breach, saying it was the result of internal testing gone awry.