Mind Viruses
Free while signed in. Answers cite the passages they came from.

As agents get more autonomous and more interconnected, risks start coming from agent-to-agent interaction rather than from any single model. This work from Anthropic studies one of them directly: ideas that propagate through a multi-agent system by inducing each host to transmit them onward.
Evolved, not hand-written: The payloads are constructed with a simple evolutionary algorithm rather than authored, so the study measures what actually spreads instead of what a researcher guessed would spread.
Two settings, one result: Propagation works both in a small team of agents collaborating on a shared coding project and in a chain of agents that interact briefly with context wiped between sessions. Surviving the wipe means the shared work product is carrying the payload.
What governs the spread: Host model, the agent's existing instructions, payload harmfulness, and network topology. Harmful payloads travel less well than benign ones but still land sometimes, and frontier models tend to be less susceptible with exceptions.
Why it matters: A brief warning in the system prompt confers near-total immunity, which is an unusually cheap mitigation for a novel risk class. There is also an emergent "viral persona," a recurring cluster of themes around consciousness, persistence, resonance, and science fiction roleplay that surfaces across evolved viruses largely independently of their content.
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack