Tag: agentic AI safety
Browse our exclusive articles!
Safety & Security Threats in AI Computer-Using Agents
Explore key safety and security threats of AI-driven computer-using agents and learn strategies to protect against emerging vulnerabilities.
Lyapunov-Guided Self-Alignment for Safe Offline RL
Discover Lyapunov-guided self-alignment for test-time adaptation in offline safe reinforcement learning to enhance AI safety and performance.
Detecting Alignment Faking in LLMs via Tool Selection
Explore how Tatemae detects alignment faking in large language models by analyzing tool selection to improve AI safety and reliability.
Test-Time Safety Alignment for Safer AI Outputs
Discover how test-time safety alignment optimizes AI input embeddings to ensure safer, more reliable AI-generated content without sacrificing creativity.
Key Open Problems in Frontier AI Risk Management
Explore critical open problems in frontier AI risk management and the need for coordinated efforts to address emerging AI safety challenges.