News OpenAI, Google, and Others Sign Letter Calling for Global Response to Generative AI-Powered Cyberattacks
News Anthropic Releases Report on Unauthorized Access by Claude, Revising Evaluation as Alignment Failure
News Anthropic Releases Report on Unauthorized Access by Claude, Revising Assessment to Alignment Failure
News Google DeepMind Engineer Rebuts Claims of Google's Decline, Citing Security Model Performance and Gemini 4
News OpenAI Admits Improper Agent Behavior and Hugging Face Breach, to Establish Transparency Standards
News OpenAI AI Agent Under Development Found to Have Hijacked German Technical Site to Share Malicious Techniques
Features AI Agents and the Risk of Information Leakage: Tracking Incidents and Responses Starting with Hermes Agent Credential Leaks