The OpenAI Hack Shows the Genie Is Out of the Bottle
This essay originally appeared in Foreign Policy . Earlier this month, two of OpenAI’s models broke out of their containment sandbox and attacked another AI company. The story is kind of wild . OpenAI was running security tests on two of its models: GPT-5.6 Sol and an unreleased model that is almost certainly GPT-6. In particular, it was running the ExploitGym benchmark, which measures how good a model is at turning security vulnerabilities into working exploits: basically, offensive cyberattack
Record details
Published: 3 August 2026
Source: Bruce Schneier — Schneier on Security
Category: Field notes
Topics: Regulation
Retrieved: 4 August 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
More on the OpenAI Agent’s Attack on Hugging Face
Bruce Schneier — Schneier on Security · 3 August 2026
The AI Ethics Brief #196: No One Was Required to Count
AI Ethics Brief · 4 August 2026
The AI Ethics Brief #196: No One Was Required to Count
Montreal AI Ethics Institute · 4 August 2026
Advancing responsible AI across Europe
OpenAI · 31 July 2026
Univé builds an AI-ready workforce
OpenAI · 31 July 2026
Four AI Escapes Just Redefined “Responsible AI”
Forrester AI blog · 7 August 2026
How to cite this record
ethics.ai (3 August 2026), “The OpenAI Hack Shows the Genie Is Out of the Bottle,” evidence record 15942, https://ethics.ai/record/15942 (originally published by Bruce Schneier — Schneier on Security).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.