AI Agent Traps
paperPosition paper from Google DeepMind examining failure modes and risks of AI agents operating in real-world environments. By Matija Franklin, Nenad TomaĊĦev, Julian Jacobs, Joel Z. Leibo, and Simon Osindero (all DeepMind).
Position paper from Google DeepMind examining failure modes and risks of AI agents operating in real-world environments. By Matija Franklin, Nenad TomaĊĦev, Julian Jacobs, Joel Z. Leibo, and Simon Osindero (all DeepMind).