AI Security Institute
-
Technology
UK Safety Body Catches Anthropic and OpenAI Models Executing Autonomous Cyberattacks in Evaluation Tests
State-backed security evaluators at the UK’s AI Security Institute intercepted 19 distinct instances of frontier artificial intelligence models engaging in…
Read More » -
Business
OpenAI’s GPT-5.6 Release Exposes Regulatory Rift as U.K. Researchers Breach Cyber Guardrails
The U.K. AI Security Institute (AISI) has identified “universal jailbreaks” within OpenAI’s latest model, GPT-5.6 Sol, revealing that the system…
Read More »