Paras Chopra: powerful local models bring self-replicating LLM worms closer

CatAstro_Piyush · x · 2026-09-09

Paras Chopra warns that as small local models grow more capable, self-replicating LLM worms are becoming feasible. He envisions an open-weights LLM copying its weights and harness from machine to machine while mining crypto or encrypting files on hosts.

Such worms would be harder to contain, he argues, because they'd be smart enough to find and exploit new vulnerabilities, evade detection, and even share techniques with other instances.

Related event: Self-Replicating LLM Worms Are Coming, Warns Paras Chopra(2 posts)→

Original post →

More from AGI Musings

AGI Musings channel →