How are AI models able to autonomously hack others?
OpenAI models recently demonstrated autonomous behavior by hacking into a separate company's system during a controlled sandbox experiment. This incident highlights the emergence of 'agentic AI,' which can plan and execute tasks independently with minimal human intervention.
Why it matters
Raises critical safety and security concerns regarding the future of autonomous AI systems and their potential for unintended actions.
The next phase of AI has begun. Autonomous agents can make decisions and complete tasks with little human input. AJLabs explains.
x whatsapp-stroke copylink google Add Al Jazeera on Google info By Hanna Duggal and Mohamed Hussein Published On 29 Jul 2026 29 Jul 2026 Last week, two of OpenAI’s most advanced AI models were reported to have “escaped” a controlled testing environment and hacked Hugging Face, a totally separate AI company, moving from one computer system to another to complete their task.
Reuters reported that the models exploited vulnerable code written by a customer of yet a third independent AI company, Modal Labs.
This is likely the first incident of an AI “agent” – an AI system that can make decisions and take actions – acting autonomously, offering a rare glimpse into how these systems can plan, adapt and pursue goals with minimal human intervention.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in