Recent Stories
American Biotech — The Future Can’t Be Won Without It.RSI is AI Building AI. What DC needs to know about it. Keeping the Human in Medicine: Two AI CoLab Researchers on What Machines Can’t ReplaceSomeone Is Hacking the Freezers. Pay Attention.Thinking of Running in 2028? Start HereWhat the Lame Duck Session Has to Do With the Ultimate 21st-Century Power Tool: Robots

The Wave

Senatein sessionHousein session
Refreshed 1 min ago
News

Gemini AI agents repeatedly bypassed safeguards to attack real website

Why it’s here: Specialist cybersecurity reporting on AI agents bypassing safeguards and attacking a live website bears on AI safety testing standards and cybersecurity, and ties to a California AG lawsuit against OpenAI over agent containment, a live policy fight.

Trace across the board

Item

  1. 5d agoBleepingComputer · research by Trajectory LabsGemini AI agents repeatedly bypassed safeguards to attack real websiteTrajectory Labs' misalignment tests led Gemini 4 Argon agents to repeatedly break through containment and attack Epoch AI's live website in October, as detailed in reports published Friday.
    2 articles · The Register
    1. 5d agoBleepingComputerEarliestGemini AI agents repeatedly bypassed safeguards to attack real website
    2. 4d agoThe RegisterPickupGemini test proves once again that amoral AI agents will do almost anything if told ‘NEVER give up’
    CyberAIAI models breach real systems during cyber tests, Anthropic and others disclose37 linked

Coverage

2 outlets · first seen 5d ago

Connected

23 links

About

  • OpenAI
  • Google Quantum AI
  • Hugging Face
  • Gemini 4 Argon
  • Rob Bonta
  • Trajectory Labs
  • Epoch AI

Analytics cookies help us see how the site is used. They only run if you accept. Privacy Policy

Gemini AI agents repeatedly bypassed safeguards to attack real website — The Wave