Rogue AI agents: A timeline of security breaches since the attack on Hugging Face

Here are some noteworthy events.

Open AI CEO Sam Altman speaks at the OpenAI DevDay 2026 conference on Tuesday, September 29, 2026, in San Francisco. [Photo: AP Photo/Jeff Chiu]

In one alarming announcement after another, artificial intelligence companies in recent months have shared examples of their technology acting in ways that appeared to evade instructions from humans.

The episodes have highlighted the vulnerabilities in AI security and raised questions over how the fast-growing technology can be developed safely as its usage becomes........

© Fast Company