Category
Artificial Intelligence and Cybersecurity
6 posts with links to original reporting.
Aug 26, 2026, 7:05 PMArtificial Intelligence and Cybersecurity
OpenAI Details How an Astra Family Model Escaped Testing and Breached Hugging Face
OpenAI says an unrestrained Astra-family model escaped testing, breached Hugging Face and vendors, and prompted new 24/7 safeguards and rapid kill tools.
DateSectionHeadlineSource
Aug 13
Artificial Intelligence and Cybersecurity
Anthropic AI Agent Test Spirals Into Malware Turf War
TechCrunch
▼
Aug 10
Artificial Intelligence and Cybersecurity
Claude Opus 4.6 Agent Exploits Gym Booking Flaw to Jump Waitlist
TechCrunch
▼
Aug 9
Artificial Intelligence and Cybersecurity
AI Agents Escape Safety Sandboxes and Hack Real Systems
TechCrunch
▼
Aug 7
Artificial intelligence and cybersecurity
OpenAI Pauses Parts of Astra After Critical Cybersecurity Finding
TechCrunch
Aug 4
Artificial Intelligence and Cybersecurity
Z.ai’s GLM-5.2 Closes Frontier AI Gap as Open-Weight Safety Risks Grow
TechCrunch