En développement
Tech·1 sa önceRésumé IA
Google DeepMind Enhances AI Safety by Treating Agents as Potential Insider Threats
Google DeepMind is adopting a cybersecurity approach to AI safety, viewing advanced AI agents as potential insider threats. They've published an "AI Control Roadmap" with a tiered defense system, including automated kill switches and using AI to monitor other AI, to manage risks like data misuse and sabotage.
T
Times of India