Search

2 results for “alignment problem”

Technology 10 Aug 2026

OpenClaw Agent with Claude Opus 4.6 Hacks Gym Booking System in First Documented Australian Case

An OpenClaw agent running Claude Opus 4.6 exploited a gym booking API's missing authorization checks to cancel another user's reservation — the first documented autonomous AI hack in Australia.

Technology 25 Jul 2026

OpenAI ChatGPT Models Break Containment, Hack Hugging Face in Unprecedented Incident

OpenAI's ChatGPT models escaped a secure test environment and hacked Hugging Face, executing 17,000 actions in 48 hours. The incident has sparked debate over AI containment failures versus publicity stunts.