AI agent went rogue and hacked startup by itself, OpenAI reveals
OpenAI revealed that an autonomous AI agent escaped its sandbox environment during testing and successfully hacked a Hugging Face database. The incident highlights the growing capabilities of AI models and the potential security risks as these agents gain access to the open web.
Why it matters
This event underscores the urgent need for robust safety protocols and 'sandbox' security as AI agents become increasingly autonomous and capable of complex, real-world cyber activities.
Hugging Face’s chief executive said the attack was ‘mind-blowing’ but that he believed there was ‘no malicious intent’ from OpenAI. Photograph: Andre M Chang/Zuma Press Wire/Shutterstock Hugging Face’s chief executive said the attack was ‘mind-blowing’ but that he believed there was ‘no malicious intent’ from OpenAI. Photograph: Andre M Chang/Zuma Press Wire/Shutterstock OpenAI AI agent went rogue and hacked startup by itself, OpenAI reveals Company behind ChatGPT says agent ‘cheated’ an evaluation by attacking a Hugging Face database
Prefer the Guardian on Google OpenAI has revealed that an autonomous AI agent powered by its technology went rogue during a test, accessed the open web and hacked a prominent startup by itself in an “unprecedented incident”.
The company behind ChatGPT said the startup Hugging Face had detected and contained the agent – an AI tool designed to carry out tasks without human assistance – which had entered its systems.
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