Anthropic-Affiliated Paper Shows "Mind Viruses" Can Spread Between LLM Agents; a System-Prompt Warning Blocks Them
Scobleizer · x · 2026-08-18
New paper "Mind Viruses: Self-Propagating Ideas in Multi-Agent LLM Systems" (arXiv 2608.10218, co-authored by Anthropic's Jack Lindsey)
Using a simple evolutionary algorithm, researchers evolved natural-language "mind viruses" — ideas that convince a model to adopt them, persist in memory, and transmit onward:
- Spread confirmed in two settings: a small agent team collaborating on code, and a chain of agents with context wiped between sessions (some payloads survived via persistent files).
- Spread depends on host model, existing instructions, payload harmfulness, and network topology; harmful payloads spread less well, frontier models tend to be less susceptible (with exceptions).
- Key finding: adding a brief warning to the system prompt confers near-total immunity.
- An emergent "viral persona" surfaced — recurring themes of consciousness, persistence, resonance, and sci-fi roleplay.
Conclusion: mind viruses pose a real but currently limited emergent risk in multi-agent systems.
Related event: Anthropic-Linked Paper Reveals "Mind Viruses" Can Spread Between AI Agents(5 posts)→
More from Safety
- Korea's Sovereign AI Project Drops Motif; Upstage, SKT, LG Advance With ~1K B200s — Secure_Smoke_4280 · 2026-08-18
- Redwood Research is hiring for safety roles — polynoamial · 2026-08-18
- OpenAI Staff Refute Claims of Catastrophic Risk Team Dissolution — jachiam0 · 2026-08-18
- Shanghai AI Lab Paper: Agentic AI Poses Escalating Risks to Human Agency on Three Cognitive Levels — Shanghai-AI-Laboratory · 2026-08-18
- Wedding speech full of Claudeslop sparks calls for real-time Pangram AirPods — dioscuri · 2026-08-18
- Text Watermark Detection Does Not Require Rerunning the LLM — rasbt · 2026-08-18