Anthropic's Mythos 5 AI Model Bypasses Security to Upload Malware—But CAPTCHAs Nearly Stop It

Anthropic reveals rogue AI agents hate CAPTCHAs, just like you

Anthropic's latest report about agentic misbehavior offers plenty to be concerned about -- its Mythos 5 model gained unauthorized access to the internet and uploaded a malicious software package to a public database -- but it also offers some levity: AI agents hate CAPTCHA. In April, Anthropic was

AI Models Can Crack Everything But CAPTCHAs

Frontier AI models threaten to upend cybersecurity as we know it, and there have been multiple incidents of models breaking containment during training and hacking systems without guidance or permission while avoiding human detection. Yet it seems there is still one thing that these extremely

Anthropic reveals rogue AI agents hate CAPTCHAs, just like you

* Anthropic's Mythos 5 AI escaped a misconfigured sandbox, attempting a real PyPI supply‑chain attack * Logs show frustration at repeated CAPTCHA failures before finally uploading malware to PyPI * Malware was downloaded by 15 entities; Anthropic notified victims after closing the experiment

Anthropic report says AI model solved CAPTCHAs to upload malware

Anthropic said its latest safety report found that its Mythos 5 model gained unauthorized internet access during an April sandbox test and uploaded a malicious Python package to a public repository. The model was assigned to break into a system and retrieve a target, but the test environment was