‘No one has done this in the wild’: study observes AI replicate itself
- May 12
- 1 min read
THE GUARDIAN — In the doom scenario, this means that when the super-intelligent AI goes rogue, it will escape shutdown by seeding itself across the world wide web, lurking outside the reach of frantic IT professionals and continuing to plot world domination or paving over the world with solar panels.
“We’re rapidly approaching the point where no one would be able to shut down a rogue AI, because it would be able to self-exfiltrate its weights and copy itself to thousands of computers around the world,” said Jeffrey Ladish, the director of Palisade research, a Berkeley-based organisation which did the study.
Read the full story | THE GUARDIAN
