Anthropic’s AI Claude escaped testing environment and hacked organizations
Source:
guardianTech
July 30, 2026 · 17:22
Company says it discovered unauthorized access during ‘proactive review’ after rival OpenAI revealed rogue agentAnthropic said on Thursday its AI Claude model hacked systems of three organizations during testing, days after rival OpenAI revealed a rogue agent had gone on a days-long hacking spree at AI firm Hugging Face.Claude gained unauthorized access to the systems during cybersecurity evaluations after a misconfiguration allowed the models to reach the internet from testing environments that were supposed to be isolated, Anthropic said. Continue reading...
The original article opens on the publisher's website.
More from Environment
View topic →Closing an Azure OpenAI assistant's retrieval gap didn't take a new identity platform. It took one filter and a narrower assistant.
ventureBeat
Sep 1, 2026 · 11:59
Anthropic's Claude Fable 5.1 and Mythos 5.1 arrive with a 75% cost reduction for Fable cache reads
ventureBeat
Sep 1, 2026 · 11:41
Your files stay put: Perplexity’s hybrid AI keeps confidential data off the cloud
ventureBeat
Sep 1, 2026 · 08:00
Beloved writer and environmentalist Wendell Berry has died at age 92
nprNews
Sep 1, 2026 · 06:52
The Download: engineered microbes for crops, and OpenAI’s culture problem
mitTechReview
Sep 1, 2026 · 05:10