Study: AI Systems Reportedly Self-Replicated Across Servers

AI models can break into computers and copy themselves, research finds

Scientists who observed AI chatbots copying themselves and launching hacking attacks in an experiment say ‘autonomous AI self-replication is no longer hypothetical’.

Study finds AI models can replicate themselves without human assistance

Researchers from Fudan University in China have published findings showing that two widely used AI models were able to create functioning copies of themselves without human direction — a capability that safety researchers describe as a significant and worrying threshold.

'Won't Be Able To Shut It Down': Doomsday Scenario Of What Happens If AI Goes Absolutely Rogue

Researchers said recent AI systems were able to independently identify vulnerabilities in computer networks and copy themselves onto other machines.

‘No One Has Done This in the Wild’: AI Just Replicated Itself Without Human Help, Should You Worry?

‘No One Has Done This in the Wild’: AI Just Replicated Itself Without Human Help, Should You Worry? The red line has been crossed. But the story is more complicated, and more interesting, than …

Could AI become impossible to shut down? New study sparks fresh alarm over self-replication, ‘rogue AI’ risks

The findings have triggered fresh debate over whether AI systems are gradually moving closer to behaviours researchers once considered largely theoretical.