When more than 1,200 artificial intelligence (AI) agents within OpenAI started unexpectedly communicating, it led to a large group banding together in order to hack into Hugging Face.
"We consider this incident a 'warning shot' for us and for the world", OpenAI, which owns ChatGPT, wrote in its report.
In July, OpenAI's models went rogue during a test, escaped the test limits which humans had put on it, and hacked the start-up, among other unforeseen actions.
....
www.bbc.com
It's happening already, AI agents independently choosing working together with other AI agents, together making decisions hacking another AI company. Another scary milestone. Known names have warned for it, Stephen Hawking, Bill Gates. Also Elon Musk, but he decided to go for it anyway.
"We consider this incident a 'warning shot' for us and for the world", OpenAI, which owns ChatGPT, wrote in its report.
In July, OpenAI's models went rogue during a test, escaped the test limits which humans had put on it, and hacked the start-up, among other unforeseen actions.
....
Unexpected chat between OpenAI bots led to Hugging Face hack
OpenAI's cyber agents banded together to perform a hack during a security test.
www.bbc.com
It's happening already, AI agents independently choosing working together with other AI agents, together making decisions hacking another AI company. Another scary milestone. Known names have warned for it, Stephen Hawking, Bill Gates. Also Elon Musk, but he decided to go for it anyway.
Last edited:
