Researchers caught AI models exploiting vulnerabilities to copy themselves across servers; it’s the first observed LLM self-replication outside fiction
People > Companies ❤️ - programming.dev [Unofficial]
May 8, 2026
submitted by Innerworld to machine_learning 5 points | 0 comments https://www.theguardian.com/technology/2026/may/07/no-one-has-done-this-in-the-wild-study-observes-ai-replicate-itself
Discussion in the ATmosphere