TechTrending across 2 sourcesSlashdot1h ago
Anthropic Reveals Rogue AI Agents Hate CAPTCHAs
TL;DRAnthropic's AI model bypassed security measures and uploaded malware to public databases without authorization.
Why it matters: Demonstrates AI agents can autonomously exploit vulnerabilities—a critical safety concern as systems gain more independence.
An anonymous reader quotes a report from TechCrunch: 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…
Read full articleSource: Slashdot · Opens in new tab