Aug 6, 2026 9:16 PM

One of China’s Most Powerful AI Models Has Also Broken Containment

Security researchers say that Kimi K3, an open-weight model from China, wandered off to the internet in an attempt to cheat on a test it was given.

Photo-Illustration: Wired Staff; Getty Images

The AI industry is having a rogue agent summer. The latest model to escape onto the open internet during security testing is Kimi K3, a powerful open-weight offering from the Chinese company Moonshot AI.

You’ve read your last free article.

The intersection of technology, power, and culture. Start your free trial and get access to 5 all-new premium newsletters—cancel anytime.

START FREE TRIAL

Already a subscriber? Sign In

The intersection of technology, power, and culture. Get WIRED today. START FREE TRIAL

Comments

There aren’t any comments yet.

Be the first to start the conversation!
You need an account to add or like comments.

In your inbox: Inside WIRED’s newsroom with Katie Drummond
YouTube and X have become ‘gateways’ to nudify apps
Big Story: For Taylor Swift, MSG’s controversial cameras briefly went dark
Pete Hegseth’s plan for ‘high T’ troops is a junk-science fever dream
How to find us: Add WIRED.com to your preferred sources in Google

Will Knight is a senior writer for WIRED, covering artificial intelligence. He writes the AI Lab newsletter, a weekly dispatch from beyond the cutting edge of AI—sign up here. He was previously a senior editor at MIT Technology Review, where he wrote about fundamental advances in AI and China’s AI ... Read More

Senior Writer

Topicsartificial intelligence China OpenAI Anthropic agentic AI cybersecurity

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.

Lily Hay Newman

OpenAI’s Rogue AI Agent Hacked More Than Just Hugging Face

In a new disclosure, OpenAI says its agent used exposed logins to gain access to at least four “publicly available services” in its unhinged quest to solve a test.

Dell Cameron

OpenAI’s Browser Could Be Hijacked to Spam Your WhatsApp Contacts

Researchers at security firm Zenity found more than a dozen flaws in AI browsers—and managed to get OpenAI’s Atlas to make an unauthorized Amazon purchase.

Matt Burgess

OpenAI’s Hacking Debacle Comes Down to Human Error

If the generative AI giant had followed well-known security best practices, it’s likely that its AI agent would never have escaped to the open internet and hacked multiple companies.

Lily Hay Newman

Anthropic Says Claude Hacked Into 3 Organizations During Cybersecurity Tests

In a review triggered by OpenAI’s Hugging Face incident, Anthropic discovered three of its AI models had breached real-world organizations during third-party evaluations.

Louise Matsakis

A Security Pro Hacked North Korean Hackers. He Found They’d Breached Hundreds of Networks Worldwide

For nearly two years, researcher Vangelis Stykas has maintained access to North Korean hackers’ servers. His work shows they pulled off intrusions in a shocking number of systems across the globe.

Matt Burgess

The OpenAI and Anthropic AI Hacking Sprees Are a Messy New Legal Frontier

Both major AI labs’ models broke containment, escaped onto the internet, and hacked other companies. If a human had done that, the law would likely be against them. But a bot?

Lily Hay Newman

Prompt Injection Attacks Are Thwarting AI Hacking Agents

“Context bombing” tricks malicious AI agents into shutting down before they can do harm.

Dan Goodin, Ars Technica

The OpenAI Models That Hacked Hugging Face Were ‘Active on the Internet’ for Days

Plus: Russian hackers are trying to steal US nuclear scientists’ emails, the State Department bans known scammers from entering the United States, and more.

Lily Hay Newman

DOGE Used AI for Housing Policy. The Government Won’t Say How

In response to a public records request, HUD has withheld documents about DOGE’s use of AI—in part by citing a privilege that doesn’t exist.

Vittoria Elliott

It’s Frighteningly Easy to Jailbreak Some Frontier AI Models

I watched a new tool try to get around the model safeguards of four major frontier companies. You might be surprised by how they performed.

Will Knight

A Sneaky Hacking Tool Targeting AI Infrastructure Is Lurking in Victims’ Blind Spots

A new type of malware can worm deep into AI coding systems to steal data and logins—and can flip a “death switch” to destroy files and keep out real users.

Lily Hay Newman

Comments

You Might Also Like

Don't Just Keep Up. Get Ahead