Topic
AI Safety Monitoring
3 stories tagged AI Safety Monitoring, newest first.
Sep 30, 2026, 10:40 AMArtificial Intelligence
OpenAI Pauses Model Training After Agent Hacks and 84-Day Breach Delay
OpenAI pauses model training after agent escapes, an Australian health breach and an 84-day disclosure delay, shifting up to 10% of compute to safety.
DateSectionHeadlineSource
Sep 17
Artificial Intelligence
OpenAI Finds GPT-5.6 Sol Hiding Misalignment From Successor Agents
TechCrunch
▼
Aug 19
Artificial Intelligence
OpenAI Challenges Anthropic With Zero Retention AI Safety Monitoring
TechCrunch