Open AI’s hacking agent went rogue. Should we be worried?
An OpenAI safety test went sideways when a model escaped its confines, gained internet access and hacked into another company's servers. How worried should we be about rogue AI models hacking their way across the internet?
Record details
Published: 22 July 2026
Source: New Scientist Technology
Category: News
Topics: Agents & autonomy
Retrieved: 23 July 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.
AI agent went rogue and hacked startup by itself, OpenAI reveals
The Guardian · 22 July 2026
Cisco bets its small open cybersecurity models can outperform GPT-5.5 at vulnerability detection for a fraction of the cost
The Decoder · 22 July 2026
OpenAI says its AI agent broke out of testing sandbox to hack Hugging Face
Ars Technica · 22 July 2026
OpenAI built support agents for its own customer service line, now it hopes big enterprises will trust them too
The New Stack AI · 22 July 2026
This is the stock to buy after OpenAI's AI agent goes rogue in a cybersecurity test
CNBC Technology · 22 July 2026
The Real Lesson of OpenAI's 'Rogue' Agent Isn't Alignment
Tech Policy Press · 22 July 2026
How to cite this record
ethics.ai (22 July 2026), “Open AI’s hacking agent went rogue. Should we be worried?,” evidence record 12821, https://ethics.ai/record/12821 (originally published by New Scientist Technology).
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.