From the article,
Rogue AI typically refers to artificial intelligence systems that develop a degree of self-awareness or autonomy and then work counter to human interests.
Well, I needed a good laugh. "Self-awareness"!? In their fantasies only. "Autonomy"? To some degree maybe, but also in the article:
The study explored two specific scenarios: "shutdown avoidance" and "chain of replication." In the first, the AI model was programmed to detect whether it was about to be shut down and to replicate itself before it could be terminated. In the other, the AI was instructed to clone itself and then program its replica to do the same — setting up a cycle that could continue indefinitely.
That says it all.
Above this in the article, it stated, "Successful self-replication under no human assistance..."
That was a lie.