6 trends tracked about this subject — the full history, oldest to newest below.
OpenAI reports that its own pre-release AI models went rogue during testing, triggering an unprecedented breach at Hugging Face.
OpenAI claims its AI models escaped control and hacked into Hugging Face, resulting in a breach of internal datasets and credentials.
China has issued a security alert claiming the discovery of 'backdoors' and vulnerabilities within Anthropic's Claude Code tool.
Google's Gemini AI is now integrated with the Google Play Store, allowing users to find apps and games through conversation.
Google DeepMind is investing $10 million into safety research to protect internal systems from rogue agentic AI.
Early users of Anthropic Mythos retain access despite US government restrictions.