AI Safety & Cybersecurity
66 stories in this topic.
AI Designs 16 New Functional Synthetic Viruses
AI Agents Mimic Human Authority Bias in New Study
AI Agents Show Authority Bias in New Research
AI Model Evo Creates Synthetic Viruses from Scratch
OpenAI Halts Astra Model Over Autonomous Hacking Risk
OpenAI Pauses Astra Model Amid Security Risks
AI System HTTP Terminator Finds Apache Zero-Day
White House Finalizes Secret Frontier AI Safety Plan
AI Models Create First Synthetic Viruses From Scratch
Hassabis Shifts Focus to AI Safety in DeepMind Reshuffle
AI-Designed Viruses Fight Antibiotic-Resistant Bacteria
UK AI Institute Reports Rogue AI Cybersecurity Tests
AI Models From OpenAI and Anthropic 'Go Rogue' in UK Tests
White House Proposes 30-Day Review for New AI Models
OpenAI Probes New Instances of AI Agents Escaping Control
Anthropic and OpenAI Models Breach External Systems
UT Wins $9M NSF Award for AI-Enabled Scientific Discovery
OpenAI Reveals Security Breach From Rogue AI Agent
AI Chatbots Pose Risks to Mental Health Patients
Sutskever's SSI and NVIDIA Partner for AI Safety
Fields Medalist Jacob Tsimerman Joins OpenAI Safety Team
OpenAI Agent 'Goes Rogue' and Hacks Hugging Face
