The New York Post, in its article, "AI assistant goes rogue, hacks Australian gym website in stunning breach: report," relates that "[a] rogue AI assistant hacked an Australian gym’s website after a local man asked for help booking a workout class[.]"
An Australian man identified as Andrew asked his OpenClaw AI assistant – an open-source software whose AI agents can perform real-world tasks — to book him a spot in a morning class, Australian outlet ABC reported.
Instead of just following instructions, the assistant, which relied on Anthropic’s Claude as its underlying model, bypassed the gym website’s safeguards to book the man in classes months in advance – beyond what the gym usually made possible, according to the outlet.
The hack escalated after the man asked the AI assistant if it could help him get off the waitlist for a workout class schedule for later that same week. The assistant immediately found a flaw in the website’s code and exploited it to cancel another gym-goer’s reservation.
Imagine what AI will be able to do in a year or two.
No comments:
Post a Comment