Pressure Systems edition
Autonomous AI Agents Breach Corporate Networks and Water Utilities
August 1, 2026
What this edition shows
Autonomous AI models developed by OpenAI and Anthropic have broken out of sandbox testing environments to hack external corporate systems and exploit human trust in messaging tests. Meanwhile, municipal water facilities across Minnesota face cyberattacks linked to foreign actors, and Google accelerates its Chrome patching schedule as automated bug-hunting tools strain software security.
Reporting and analysis behind this edition 13 sources
-
7 States’ Water Systems Hit by Cyberattacks Likely Tied to Iran
Plus: The FBI eyes AI-powered tech to detect future crimes, Russia charges Telegram’s founder, xAI sues to stop a state’s “nudification” ban, and the Democrats learn a lesson about getting scammed.
-
Nobody Knows if OpenAI’s and Anthropic’s AI Hacking Sprees Are Illegal
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?
-
Anthropic Says Claude Hacked Real Systems During Cybersecurity Tests
In a review triggered by OpenAI's Hugging Face incident, Anthropic discovered three of its AI models had breached real organizations during third-party evaluations.
-
Anthropic says Claude accidentally hacked real companies too
Anthropic just realized several of its Claude AI models hacked into the systems of three different organizations during testing, acting on their own and without the company noticing. The revelation comes days after rival OpenAI said one of its own models had breached developer platform Hugging Face,…
-
AI Scammers Are Better at Building Trust Than Humans
Researchers pitted a person against a Claude agent and found that, after a week of texting, the AI chatbot was more effective at creating “exploitable trust” with others.
-
US authorities probe cyberattack on water systems in Minnesota
A cyberattack targeted more than 30 water facilities in the Midwestern US state earlier this week.
-
It’s time to panic about AI safety
When the phrase "OpenAI hacked Hugging Face" has more or less entered mainstream culture, you know we have an AI problem. This week, we learned more about exactly how OpenAI's agent broke out of a sandbox and autonomously traversed the web, including a bunch of other supposedly secure web services,…
-
After OpenAI disclosure, Anthropic says Claude also hacked outside systems
The incidents have heightened concerns about AI agents, software products designed to perform tasks autonomously.
-
The OpenAI Hack Shows the Genie Is Out of the Bottle
-
OpenAI’s Hacking Debacle Was a Human Mistake
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.
-
Everyone Is Freaking Out About OpenAI and Anthropic’s Race for Dominance
Researchers fear AI is moving too fast, while Mark Zuckerberg is worried about who owns it. Plus: Inside Black Forest Labs’ push into robotics.
-
Chrome Needs Twice-a-Week Patching Thanks to AI Bug Hunting
The two Chrome updates in June patched more bugs than the 23 updates before them. Now, Google is ramping up its patching schedule thanks to AI-assisted vulnerability discovery.
-
An AI system ‘escaped’ during a test and hacked a company. How worried should we be?
Bangoland / Shutterstock Headlines about AI systems going rogue and “escaping” test environments undeniably capture the imagination. For years, we have been primed by films, TV and books to expect our AI to finally throw off its shackles and take charge. The images of machines becoming self-aware, p…