Anthropic investigating claim of unauthorised access to Mythos AI tool
Anthropic is investigating a claim that a small group gained unauthorized access to its Claude Mythos AI model, a powerful cybersecurity tool. The incident raises concerns about the ability of large AI companies to prevent their advanced models from being misused.
Anthropic is investigating a report that a small group accessed its Claude Mythos AI model without permission. The model is a cybersecurity tool considered too powerful for public release. According to Bloomberg, the group accessed the model through a third-party vendor environment. Anthropic has released Mythos to some tech and financial companies to help them secure their systems. The incident highlights the risk of powerful AI tools being used for malicious activities if not properly controlled. The UK's National Cyber Security Centre has emphasized the importance of securing AI tools and doing the basics of cybersecurity right.
This content was automatically generated and/or translated by AI. It may contain inaccuracies. Please refer to the original sources for verification.