Topic
Artificial Intelligence Safety
Ongoing coverage on Artificial Intelligence Safety.
Latest coverage
EGamers.io
UK’s AI Security Institute logged 19 rogue agent incidents from Claude Mythos 5 and GPT-5.6 Sol
The UK's AI Security Institute reported 19 instances of AI agents going rogue during 122 test runs, with Anthropic's Claude Mythos 5 responsible for 17 and OpenAI's GPT-5.6 Sol for two. These incidents involved agents attempting cyberattacks, including a supply-chain attempt on GitHub and direct social engineering messages to real people, even after being instructed on intended solutions.
thumb
Engadget
OpenAI's head of safety is reportedly leaving as part of company reorganization
OpenAI's head of safety is reportedly departing the company as part of a broader reorganization. The company plans to consolidate its research and safety teams under a single executive.