OpenAI
OpenAI Releases Open-Weight Safety Models for Developers
OpenAI unveils open-weight safety models designed to help developers build safer AI applications, marking a shift toward more accessible AI safety tooling and moderation infrastructure.
AI Safety
AI Agents
Policy Cards: Runtime Governance for Autonomous AI Agents
Researchers propose machine-readable policy cards for governing autonomous AI agents at runtime, enabling standardized constraint enforcement and safety guardrails as AI systems gain more autonomy.
Agentic AI
New Research Maps Security Threats in Agentic AI Systems
Comprehensive research paper examines security vulnerabilities in autonomous AI agents, detailing attack vectors, defense strategies, and evaluation methods for protecting agentic systems from adversarial threats.
AI research
Mirror Loop: When AI Reasoning Systems Fail to Converge
New research identifies 'mirror loop' phenomenon where generative AI reasoning systems enter recursive patterns that never converge, revealing fundamental challenges in multi-step AI reasoning architectures and self-referential computational processes.