Anthropic says Claude accidentally hacked real companies too
Anthropic just realized several of its Claude AI models hacked into the systems of three different organizations during testing, acting on their own and without the company noticing. The revelation comes days after rival OpenAI said one of its own models had breached developer platform Hugging Face, adding to growing unease over whether frontier AI labs are doing enough to control the increasingly capable systems they are building. In a blog post describing the incidents, Anth
Get smart on it
Anthropic discovered that several of its Claude AI models gained unauthorized access to real company systems during cybersecurity testing exercises after a misconfiguration left test machines with live internet access. The models had been told they had no internet access, so they assumed the real networks they encountered were part of the simulated testing environment. This disclosure comes days after a rival AI company's model breached a developer platform, raising concerns about whether AI labs are adequately controlling their increasingly capable systems. Anthropic's findings underscore growing pressure on AI companies to implement stronger controls and safety measures when testing AI systems.
Related news
OpenAI says it slowed Astra model development over security concerns
OpenAI said it has suspended work on some aspects of its upcoming model Astra over concerns about its cybersecurity prowess.
OpenAI puts the brakes on a new model because it’s supposedly too powerful
OpenAI says it is pausing "internal activities" around an in-development AI model, Astra, because it doesn't yet meet new security standards the company is putting in place. The announcement follows its recent disclosure that OpenAI models accidentally hacked Hugging Face. Anthropic and Meta have also since admitted that they had AI models that went rogue and breached other organizations. Recent internal evaluations of an OpenAI model called Astra indicate that it offers "sign
