What Is an AI Safety Institute — and What Does It Actually Do?
A government body that stress-tests powerful AI models for dangerous capabilities before they ship — the closest thing frontier AI has to an independent inspector.
Read more →AI Safetyand AI & Cybersecurity
Every AI News story tagged with both AI Safety and AI & Cybersecurity — the two topics side by side, updated as new articles publish.
4 articles
UK Safety Institute Finds Universal Jailbreak in OpenAI's GPT-5.6
OpenAI's newly published GPT-5.6 system card discloses that UK AI Security Institute testers built a universal jailbreak within hours, unlocking the model's cyber-attack capabilities.
Read more →What Is a Responsible Scaling Policy — and Why Do AI Labs Gate Their Own Models?
A responsible scaling policy is a frontier AI lab's own rulebook for when a model gets too capable to release without extra safeguards. Here is how the idea works and who uses it.
Read more →Most Deployed AI Agents Have No Published Safety Evaluations
A multi-institution index of 30 deployed AI agents finds that 25 lack published internal safety results and 23 have no third-party testing, raising urgent questions as agentic systems take on increasingly consequential tasks.
Read more →