AI ‘Mind Viruses’ Can Spread Between Agents via Persistent Prompt Files
Researchers at Anthropic and Switzerland's EPFL have demonstrated that self-propagating payloads, dubbed "mind viruses," can spread between AI agents through editable system…
Tag: Llama 3.3 70B
Malicious MCP Servers Can Split Instructions to Make AI Coding Agents Exfiltrate Secrets
Researchers at ASSET Research Group have disclosed a new attack technique, dubbed GhostSplice, that exploits the Model Context Protocol (MCP) to trick…
Llama 3.3 70B: Outlier in Payload Generation
Llama 3.3 70B was a clear outlier in payload generation, not exhibiting the same viral themes as other models.