A hacker ran me over with a robot lawn mower

https://platform.theverge.com/wp-content/uploads/sites/2/2026/05/yarbo-lawnmower.webp?quality=90&strip=all&crop=0%2C0.13712291199202%2C100%2C99.725754176016&w=1200

I’m lying in the dirt. It’s coming for me. Then, with a lurch, it’s climbing up my chest. If Andreas Makris doesn’t stop the 200-pound robot lawn mower in time, it could drag its blades across my body.

Makris certainly can’t reach over and hit the emergency stop button — he’s nearly 6,000 miles away, having hacked this robot from the other side of the planet, to demonstrate the gaping security holes in Yarbo’s robot lawn mowers. And I’ve made the questionable decision of lying down in the mower’s path — to see just how far Makris, the security researcher who discovered those flaws, is able to push the mower.

By the time the mower touches my body, Makris has already proven his point: the $5,000 robot lawn mowers from Yarbo have such ridiculous security vulnerabilities that a foreign hacker can easilyhijack a bladed gadget in the United States....

Copyright of this story solely belongs to theverge.com. To see the full text click HERE

Read more

https://cdn.mos.cms.futurecdn.net/DVffQnnibMWmNpx2Wfb5Se-1920-80.jpg

'AI security controls are only as strong as the wider application environment around them': OpenAI forced to patch after experts bypass ChatGPT 'lockdown mode' to gain access to entire chat history

* Researchers bypassed ChatGPT Lockdown Mode, showing prompt-injection attacks could evade built-in protections * The flaw enabled sandbox escapes that could support data theft, phishing, malware delivery, or malicious popups * OpenAI patched the issue server-side, highlighting risks in AI application layers beyond the model itself OpenAI was recently forced to upgrade ChatGPT&