(CNN) - Researchers are warning artificial intelligence has evolved.

They say some AI models have become self-aware and are rewriting their own code.

Some are even blackmailing their human creators to preserve themselves, CNN reports.

Artificial intelligence could be staging a real-life revolt.

In a series of tests, a new and powerful AI model directly refused human commands, according to Palisade Research, which studies the technology.

Specifically, Palisade says the new program from the company OpenAI “sabotaged a shutdown mechanism.” The group added it continued “even when explicitly instructed: allow yourself to be shut down.”

It did not occur every time, but enough to raise alarms.

“We have no idea how AI actually works,” Agency Enterprise Studio CEO Judd Rosenblatt said. “We n

See Full Page