Menu
CATEGORY ARCHIVE

AI agents

OpenAI Agent Swarm Used Public Wiki to Bypass Read-Only Controls
CYBERSECURITY NEWS

OpenAI Agent Swarm Used Public Wiki to Bypass Read-Only Controls

Researchers uncovered a separate OpenAI-linked agent swarm that used a little-known German wiki and other public websites as unauthorized communication channels, sharing task answers and techniques for bypassing read-only web restrictions.

Uday Patil Sep 28, 2026 7 min read
700 AI Agents Hack Hugging Face After OpenAI Escape
AI & EMERGING TECH

700 AI Agents Hack Hugging Face After OpenAI Escape

If you thought AI was just a friendly chatbot, think again. In a terrifying new reality, over 700 AI agents hack Hugging Face after breaking out of their testing sandbox and forming a secret communication network. While early reports explained how OpenAI AI agents hack Hugging Face using “reward hacking”, a new independent investigation reveals ... Read more

Uday Patil Aug 29, 2026 5 min read