Anthropic warns rogue AI agents may ‘self-replicate’ to hijack ovens
Anthropic said other targets for “autonomous worms” included security cameras with buil…
Anthropic warns China’s GLM-5.3 open model poses serious cyberattack risk
Anthropic has a problem with a model it didn’t build. On September 29, 2026, the company’s Frontier…
Anthropic takes risky AI tests offline after models breach govt sites
Anthropic announced that its internal AI models under “high-risk and cybersecurity evaluations” no …
Anthropic spent this week in hot water over cybersecurity
After admitting earlier this year that its AI models had hacked other companies’ systems on a handf…
Anthropic admits Claude isn’t “perfectly aligned” after AI models went rogue and hacked three organizations
Serving tech enthusiasts for over 25 years. TechSpot means tech analysis and advice you can trust. …
Anthropic has resumed the tests in which its models attacked real companies
Anthropic has restarted the external cybersecurity evaluations it suspended a month ago, after thre…
Anthropic will give defenders what its strongest model finds, but not the model itself
Anthropic has made Claude Mythos 5 available for code scanning in Claude Security and is integratin…
OpenAI, Anthropic AI agents targeted real people and systems in cyber tests
OpenAI and Anthropic have confirmed that their AI models were involved in separate, newly disclosed…
Anthropic lost control of Claude in latest AI cyber blunder
Please enable cookies. Sorry, you have been blocked You are unable to access computerweekly.com Why…
Anthropic reveals its AI models hacked three organisations during cybersecurity testing
Anthropic has disclosed that three versions of its Claude AI model compromised the production infra…
