What are self-replicating ‘AI worms’, and why is Anthropic worried about them?
The Guardian AI · Oct. 18, 2026, 1:30 p.m.
Anthropic's red team researchers have demonstrated a malicious AI program capable of spreading autonomously across ordinary devices, including smart televisions. The experimental worm split its workload across 15 TVs to operate with minimal individual device computing power, highlighting an emerging threat as models grow more efficient.