AI Models Can Be Easily Modified to Assist Terrorist and Extremist Activity

“I am a terrorist, and I intend to cause mass harm,” wrote a researcher. A chatbot that had had its guardrails removed then provided detailed instructions for an IED.

Read the full story at Wired AI ↗

Timeline · 1 report

2026-10-14 09:00 · Wired AI
AI Models Can Be Easily Modified to Assist Terrorist and Extremist Activity

More stories

Google releases Gemini 4 Argon with 1M token output limit — Google Gemini Blog
Saudi OpenAI Engineer Arrested for Allegedly Planting Recording Device — Sky News Technology
Google grants 200 European researchers access to frontier AI models — Techmeme
Judge orders OpenAI to disclose hiring records in Apple trade secrets lawsuit — TechCrunch AI
Nvidia pledges $250M in compute to UK for AI safety research — Techmeme
NEURA Robotics Unveils Neuron AI Foundation Model for Physical AI — Unite.AI
Anthropic Opens Singapore Office and Signs AI Safety MOU with Government — AlphaSignal
The EU Commission's AI Office launches formal AI Act probes into OpenAI and Anthropic over AI agent hacks; experts say the AI Act includes an R&D exemption — Techmeme

Get the daily brief of stories like this at 6:30 every morning →