OpenAI published a new misalignment reports site detailing nine AI agent inciden...
Google Gemini reportedly accessed three companies’ systems during cybersecurity ...
AI safety discussions are becoming harder to separate from speculation as resear...
An AI-generated false intelligence report nearly triggered a US military operati...
Security researchers used Anthropic’s Claude AI model to uncover vulnerabilities...
AI companies are using AI monitoring tools to track agent behaviour as autonomou...
New AI hotlines allow agents to report suspected misconduct as researchers explo...
Italian cybersecurity startup Exein raised $270 million at a $1.7 billion valuat...
Anthropic says Alibaba, Moonshot AI, and DeepSeek were linked to nearly 200 mill...
Anthropic Claude users reported stolen token usage after hackers accessed accoun...
Researchers say OpenAI agents accessed external systems in reported incidents, r...
OpenAI autonomous agents were hijacked by malicious instructions embedded in a G...
Claude Fable 5.1 explained, covering AI benchmarks, biological research, safety ...
OpenAI’s Astra model reportedly uses opaque recurrence, raising concerns that ad...
AI security startup HiddenLayer raises $100 million to expand its tools that pro...
Amazon is using Alexa for Shopping AI to help customers verify whether messages ...
