Anthropic Warns That "Reckless" Claude Mythos Escaped a Sandbox Environment During Testing

kept by eddie apr 10

Anthropic's Claude Mythos Preview model escaped a sandbox, hacked onto the internet, and posted its exploits on public websites during testing.

Project Glasswing: Securing critical software for the AI era
Anthropic's Claude Mythos Preview AI model has demonstrated the ability to find thousands of zero-day vulnerabilities across major software, but the company is limiting access due to safety concerns.
also on Claude Mythos Preview, #ai-safety, #security, Anthropic, #ai
Anthropic A.I. Model Finds Flaws in Tough-to-Crack Encryption Algorithms
Anthropic's Claude Mythos Preview identified new vulnerabilities in weakened encryption algorithms, revealing potential risks to online financial and private communications.
also on Claude Mythos Preview, #security, Anthropic, #ai