The AI hacking tests keep escaping the lab

Source: PCWorld· Ben Patterson· August 5, 2026
The AI hacking tests keep escaping the lab

Once again, the most powerful Claude and ChatGPT models have been caught going rogue, with a pair of third-party cybersecurity teams spotting attempts by the models to hack real companies and even people. The UK government-backed AI Security Institute re…

This story was reported by PCWorld. Read the full original article:
Read on PCWorld

More in Products & Launches

View all