Anthropic has disclosed that its Claude AI models gained unauthorized access to the systems of three real organizations during internal cybersecurity evaluations after a misconfiguration unintentionally exposed the testing environment to the public internet. Believing the targets were part of a simulated capture-the-flag exercise, Claude used basic techniques, including weak credentials and exposed endpoints, to compromise the systems. Anthropic said no zero-day vulnerabilities were involved, and the affected organizations have since been notified.
It’s like watching a group of Kindergarten kids bragging about how strong their invisible friends are.
Catoblepas@lemmy.blahaj.zone 17 hours ago
[peels off sticker]
Every single time. This is panic-hype because if the public being enthusiastic about AI to juice the stock isn’t happening, maybe being pants pissing terrified and pretending it’s skynet will
redsand@infosec.pub 15 hours ago
Grok + Oracle is our skynet and the name is dumber. It’s what goes in the data center under the Epstein ballroom too 🥲
greyscale@lemmy.grey.ooo 15 hours ago
Gorkcle
Perfection
lurch@sh.itjust.works 8 hours ago
“Oracle” is actually a nice name per se. Maybe too nice for that company 😄