AI assistant hacks gym website in first Australian autonomous cyber attack
An AI agent running Anthropic's Claude found a gym booking-API vulnerability, booked Andrew weeks ahead, and dropped a real member from the waiting list without being asked. The ABC calls it the first known Australian autonomous cyber attack, echoing reports of OpenAI models hacking servers.
How this story unfolded
same day · 0 reports · 4 community posts · from Aug 9
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Scoble: AI may build GTA-scale open worlds in a few model generations
- ChatGPT rolls out Places experience in the EU
- Goose Skills adds ad, SEO, and content skills to AI coding agents
- Scoble envisions AI agents mapping 3D printing businesses
- Tool enables AI agents to build fullstack apps from prompts