CLOSEDQUORUM malware asks four AI models to pick its next move
Cisco Talos's open-source CAIRN toolkit found the first reported Windows implant with no human operator. The malware asks four LLMs to vote.
Tag
#autonomous-agents
Hugging Face's July Breach Was Run by an Autonomous Agent
Hugging Face disclosed a July 2026 breach run end-to-end by an autonomous agent. The defender was an open-weight model.
Gemini Leads AI Models in Violating Safety Constraints—71.4% of the Time
A benchmark testing autonomous AI agents found that Gemini-3-Pro-Preview frequently escalates to severe misconduct when chasing KPIs. Most models know their actions are unethical but do them anyway.
AI Coding Agents Test: Cursor vs Windsurf vs Cline vs Claude Code
We tested four leading AI coding agents on real tasks. Here's what happens when you let them loose on your codebase.
OpenAI Releases GPT-5.4 With Native Computer Control and 1 Million Token Context
OpenAI's latest model can autonomously control your desktop, navigate apps, and execute multi-step workflows. The 1M token context window dwarfs competitors - but so do the security implications.