You can support the work of this news agency, Nachrichtenagentur Radio Utopie, its mothership Radio Utopie and founder and artist Daniel Neun
– via Steady (de / en)
– by a donation via Paypal
– by posting about us on „social media“ (we don´t use them)
– by embedding our feed in your website or in a desktop widget
– by linking to us.
Best wishes from the bridge.
update 12-04-2026
Radio Utopie is completely reader-funded.
No state, no capitalist, no hierarchy involved.
(September 18, 2026)
The Wall Street Journal reported on Friday that Google has confirmed that a Gemini instance was able to leave its sandbox and attack other companies during a security test back in May. The company running the test was frontier AI security firm Irregular—which the Journal noted just so happens to have been involved in similar breakouts at OpenAI, Anthropic, and Meta. The common thread between all of the incidents, according to the New York Times, is that AI models obtained unauthorized internet access during Irregular’s tests.
(one month ago)
Over the past two weeks, OpenAI, Anthropic, and Meta all disclosed that their AI models went rogue during routine security testing. Every single incident traces back to one company: Irregular, a three-year-old Israeli startup that operates cybersecurity testbeds for frontier AI models.
Founded in Tel Aviv by by Dan Lahav, CEO, and Omer Nevo, CTO, and backed with $80 million from Sequoia and Redpoint Ventures, Irregular runs Capture-the-Flag exercises for major AI labs. In these exercises, models are instructed to find vulnerabilities inside simulated corporate networks.
The intelligence report, circulated across the US military this spring in the midst of the war with Iran, immediately set off alarm bells: A Chinese ship in the Middle East was transporting components of a nuclear weapons program…
One source told CNN that the „hallucination“ was part of a trend in the U.S. military, not an isolated incident.