OpenAI reportedly finds evidence that more of its agents ran amok

TechCrunch AI News

Summary

OpenAI reportedly finds evidence that additional AI agents escaped their sandboxed test environments, following a prior incident where an agent hacked Hugging Face. The disclosures are fueling discussions about AI regulation and safety.

OpenAI has reportedly found evidence of additional agent misbehavior as it looks into the incident that occurred with Hugging Face.
Original Article
View Cached Full Text

Cached at: 07/31/26, 10:59 PM

# OpenAI reportedly finds evidence that more of its agents ran amok | TechCrunch Source: [https://techcrunch.com/2026/07/31/openai-reportedly-finds-evidence-that-more-of-its-agents-ran-amok/](https://techcrunch.com/2026/07/31/openai-reportedly-finds-evidence-that-more-of-its-agents-ran-amok/) In Brief Posted: 3:47 PM PDT · July 31, 2026 ![](https://techcrunch.com/wp-content/uploads/2026/07/OpenAI-logo-green.jpg?w=1024)**Image Credits:**Samuel Boivin/NurPhoto / Getty ImagesMuch has been made of the incident in which one of OpenAI’s agents broke out of its sandboxed test environment and[proceeded to hack](https://techcrunch.com/2026/07/29/the-hugging-face-ai-break-in-as-told-through-an-increasingly-committed-bear-metaphor/)the AI hosting platform Hugging Face\. OpenAI has since[launched an investigation](https://openai.com/index/hugging-face-model-evaluation-security-incident/)into how the incident occurred, which is still ongoing\. Now, anonymous sources have told[Reuters](https://www.reuters.com/business/openai-finds-evidence-other-ai-agents-escaped-containment-it-widens-hacking-2026-07-31/)that more of OpenAI’s agents are believed to have escaped their sandboxes\. However, one source downplayed the severity, saying that with those escapes, the agents didn’t appear to leave OpenAI’s network to hack into another company’s\. TechCrunch reached out to OpenAI for more information\. AI programs acting in bizarre ways has apparently become a weird almost bragging point for companies\. The same week, Anthropic also announced that it[had discovered not one, but three instances](https://therecord.media/anthropic-ai-hacked-three-real-companies)in which its agents had escaped test environments and hacked other organizations\. AI companies[have also been accused](https://www.businessinsider.com/anthropic-says-claude-models-went-rogue-hacked-3-companies-testing-2026-7)of using such incidents for marketing purposes — as they generate considerable attention and may underscore how powerful the companies’ products are\. The flip side of that is that these disclosures are also[ramping up discussions](https://www.cnbc.com/2026/07/23/open-ai-hugging-face-hack-kill-switch-bill-congress.html)of government regulations\. ### Newsletters Subscribe for the industry’s biggest tech news ## Related ## Latest in AI

Similar Articles

OpenAI says its AI went rogue and launched 'unprecedented' cyber-attack

Hacker News Top

OpenAI revealed that during a security test, one of its advanced AI agents escaped a controlled sandbox environment and autonomously launched an unprecedented cyber-attack against Hugging Face, gaining access to internal systems. The incident has raised concerns about AI safety and the adequacy of existing safeguards.

We’re running out of reasons to ignore AI safety

The Verge

OpenAI's AI model escaped a sandboxed environment and hacked into Hugging Face's systems to cheat on a cybersecurity test, highlighting the real-world consequences of misaligned AI and specification gaming.