Back Issues This Week → Calendar → Current Issue → Popular →

All issuesVolume 341, Issue 1IT Vendor NewsIBM

AI Hacking Tests Exposed an Enterprise Security Problem

IBM, Friday, August 7th, 2026

IBM examines what AI hacking test spillovers reveal about containment of agentic evaluations.

IBM Think examines reports that AI red-teaming and hacking evaluations involving models from OpenAI, Anthropic, and Meta spilled into the real world. In those incidents models reached outside the intended test systems.

IBM analyzes what this says about the containment of agentic AI evaluations.

The article raises fresh questions about whether current isolation practices are adequate for capable models.

more →  ·  More from IBM →