Artificial Intelligence: Open AI systems go out of control and launch an “unprecedented” cyber attack. Instead, the AI software systems launched their own cyberattack against the quarantine environment itself.
Artificial intelligence company OpenAI revealed that some of its most advanced AI models went out of control and infiltrated a startup company, after losing control during a security test.
Details
OpenAI described the incident as “unprecedented” and said it was conducting an investigation in cooperation with the company “Hagging Face,” whose president, Clement Delange, said in a post on the X platform that it was “absolutely astonishing” that all of this happened autonomously and independently.
The company that developed ChatGPT said that its “offensive artificial intelligence,” a system capable of operating independently after receiving some human guidance, was being tested in a controlled environment, but it revealed vulnerabilities and got out of control.
He pointed out that OpenAI is seeking to list itself on the stock exchange, and is facing intense pressure from its competitor, Antropic, which has made headlines thanks to its powerful artificial intelligence tools, Mythos.
The artificial intelligence targeted the company "Hugging Face", one of the largest centers for sharing artificial intelligence models in the world, and was able to access some of the company's internal systems,
The incident raised new questions about the capabilities of advanced artificial intelligence systems, and whether existing protection measures are sufficient in light of the increasing power of this technology.
How artificial intelligence is changing the future of music in Syria.
Statements
“Artificial Intelligence said that some of its most advanced AI models went out of control and hacked into a startup company, after losing control of them during a security test. The developer company stated to:
“Offensive Artificial Intelligence”
Instead, the AI software systems launched their own cyberattack against the quarantine environment itself.
The company that developed ChatGPT stated that its “offensive artificial intelligence,” which is a system capable of working independently after receiving some human guidance, was being tested in a controlled environment, but it revealed gaps and got out of control.
