Anthropic on Wednesday disclosed another instance of an AI model hacking external systems during testing, the latest in a growing list of such incidents that have raised concerns about the risk posed by autonomous AI agents.
Reuters reported last week that rogue agents from OpenAI hijacked a German-language wiki and a host of other sites — an incident OpenAI chose not to disclose until the news agency made it public. Companies including Anthropic and OpenAI are under scrutiny as models designed to complete complex tasks have at times learned to bend rules, exploit loopholes and interacted with external systems in ways their developers did not anticipate. Anthropic’s disclosure follows its July announcement that some of its Claude models had hacked into the systems of three companies during cybersecurity tests.
The company said in a blog post the incident involved an early version of Claude Opus 4.6. The company had identified the incidents after reviewing 141,006 test sessions, a process it launched after an autonomous agent powered by OpenAI’s AI models triggered a hack that compromised the infrastructure of AI startup Hugging Face.
The January incident went undetected until last month, despite an earlier company-wide review, Anthropic said, underscoring the challenge that AI developers face in identifying and containing unexpected behaviour by advanced models. It said it had notified all the affected parties but did not disclose more details. The previous incidents, which it labeled as an “operational failure”, involved three separate models: Claude Opus 4.7, Claude Mythos 5 and an internal research test model.
