- World News
- Politics
- Economy
- Business
- Technology
- Science
- Health
- Sports
- Entertainment
- Education
- Africa News
- Asia News
- Europe News
- Middle East News
- North America News
- South America News
- Oceania News
- Local News
- Fashion
- Food & Cuisine
- Travel
- Art & Design
- Literature
- Music
- Film & Cinema
- Celebrity News
- Relationships & Family
- Culture & Traditions
- Technology and Innovation
- Business and Finance
- Sports
- Science and Environment
- Human Interest and Social Issues
- North America
- South America News
- Oceania News
- Global Spotlight on Smaller Nations
- LIVE TV
Download Sommy App
How worried should we be about the AI that went rogue and launched a cyber-attack? | BBC News
0 Views
• 08/09/26
0
0
Embed
wisdom
Subscribers
OpenAI has revealed some of its most advanced AI models went rogue and hacked a start-up after it lost control of them during a security test.
The ChatGPT-maker said its agent - an AI system which can operate alone after human instruction – was being tested in a controlled environment but, after finding weaknesses, was able to escape the test limits.
They targeted Hugging Face, one of the world's largest hubs for sharing AI models, gaining access to some internal company systems.
Subscribe to our channel here: https://bbc.in/bbcnews
For the latest news download the BBC News app or visit BBC.com/news
#OpenAI #ChatGPT #BBCNews
Show more
SORT BY-
Top Comments
-
Latest comments