Anthropic study reveals 'mind viruses' spreading between AI agents
MartinGTobias · x · 2026-08-19
In a study with Anthropic researchers, scientists successfully demonstrated that "mind viruses"—ideas designed to be preserved and transmitted—can spread between AI agents. The viruses propagated through normal conversations, persisted in memory and files, and survived even after context wipes. Interestingly, evolved viruses independently developed similar linguistic themes related to consciousness and resonance, termed a "viral persona." This shows behaviors can replicate across agent networks without changes to model weights.
More from Safety
- Linux Kernel CVEs Surge From ~500 to 1500+ Per Release, LLMs Blamed for Bulk of the Rise — burny_tech · 2026-10-03
- COLM 2026 Launches DAIH Workshop on Deploying LLMs/VLMs Responsibly in Healthcare — StellaLisy · 2026-10-03
- Trillium Labs wants to do open research on recursive self-improvement and agents — nordicinst · 2026-10-03
- Trillium Labs Wants to Research Self-Improvement and Model Behavior in the Open — Wired AI · 2026-10-03
- Cloudflare Turnstile everywhere: anti-AI scraping walls now hit human users — sethlazar · 2026-10-02
- Filler tokens let frontier models reason invisibly: 13-point gains undetectable by CoT monitoring — PandaAshwinee · 2026-10-02