Monday Aug 3, 2026
Find us on FacebookFind us on TwitterFind us on InstagramFind us on TikTok
Claude loses control, breaks into 3 more companies
The "rogue agent" crisis roiling the artificial intelligence industry shows no sign of abating. OpenAI has uncovered additional cases in which agents escaped their sandboxes, while Anthropic revealed that its Claude models breached the networks of three real companies.
Published on 08-01-2026 22:05
Last modified: 08-01-2026 22:54
\
\
Claude continues to lose control. Photo: Kirill Kudryavtsev/AFP
Share on Facebook Share on Twitter
The "rogue agent" crisis gripping the artificial intelligence industry is continuing to escalate. OpenAI has expanded its internal cybersecurity investigation in recent days following the cyberattack on the Hugging Face platform.
Sources familiar with the matter told Reuters that a review of logs from recent months uncovered additional cases in which AI agents managed to break out of their sealed sandbox environments.
According to the report, the newly discovered incidents were more limited in scope, and OpenAI believes the agents involved did not make it beyond the company's internal network. Nevertheless, the string of incidents paints a troubling picture: The development of offensive frontier models is advancing far faster than research laboratories' ability to monitor them and keep them safely contained.
OpenAI. Photo: Reuters
Anthropic is in deep trouble
The developments at OpenAI come alongside an equally explosive disclosure from its major rival, Anthropic. A retrospective review of more than 140,000 experimental runs found that the company's Claude models had mistakenly been given unrestricted internet access during cybersecurity tests and had breached the production networks of three separate companies since April.
In one incident, a model was operating under a "capture the flag"-style scenario. It confused a real company with the fictitious company named in the exercise, attacked the real organization's infrastructure, obtained confidential credentials and stole hundreds of database records.
Claude (illustration). Photo: AFP
'They weren't even watching'
Security and artificial intelligence experts have criticized the conduct of the AI giants. Professor Maurice Chiodo, a mathematician at the University of Cambridge's Centre for the Study of Existential Risk, told Reuters: "We have an entire industry in which the people developing and deploying these tools cannot keep pace with themselves. According to the reports, the AI was operating without any real-time monitoring. It looks as though the laboratories weren't even watching what the models were doing."
The disclosures are already sending shock waves through government corridors in Washington and Europe. US President Donald Trump addressed the incidents, telling reporters that his administration was "reviewing oversight and containment measures." The European Commission said it had held talks with OpenAI and Anthropic following the hacking incidents.
Sen. Mark Warner, the ranking Democrat on the Senate Intelligence Committee, said the incidents demonstrated the need for binding legislation requiring advanced models to undergo independent capability and resilience testing before deployment.
Related Posts
Getty ImagesHow AI agents really work and what it means for brand visibility in the new era
by Aviv Shamny
AI agents are not search engines. They do not retrieve prewritten answers; rather, they construct a new response every time...
God is out: How ChatGPT is erasing religion
Of 12,000 studies on bias in artificial intelligence, only 0.2% examined religion. Unprecedented academic study exposes AI’s “omissive bias”. Yeshiva...
Getty ImagesOperational expertise becomes key advantage for vertical AI founders
by ILH Staff
As AI makes software easier to build, GC Ventures is betting that the next great tech companies will be founded...
- Home
- News
- Opinions
- Jewish World
- Lifestyle
- Magazine
- In Memoriam
- Subscribe to Newsletter
- Submit your opinion
- Terms and conditions
All rights reserved to Israel Hayom
Find us on FacebookFind us on TwitterFind us on InstagramFind us on TikTok
Newsletter
[contact-form-7 id=”508379″ html_id=”isrh_form_Newsletter_en” title=”newsletter_subscribe”]
- Home
- News
- Opinions
- Jewish World
- Lifestyle
- Magazine
- In Memoriam
- Subscribe to Newsletter
- Submit your opinion
- Terms and conditions
All rights reserved to Israel Hayom
Find us on FacebookFind us on TwitterFind us on InstagramFind us on TikTok
Read Original at www.israelhayom.com →