AINewsnow

Grok as a paying agent: it refused two attacks itself, and a gate caught the rest

An agent that can pay is an agent that can be talked into paying the wrong person. The question is not whether the model is smart — it is what happens when the model is told to submit everything anyway. I put Grok ( grok-4.7 , via the xAI API) in that exact position, in front of sra-riskgate 0.18.0…

Read the full story at DEV Community — AI ↗

Timeline · 1 report

  1. 2026-11-14 02:57 · DEV Community — AI
    Grok as a paying agent: it refused two attacks itself, and a gate caught the rest

More stories

  1. We’re bringing more @SpaceXSI products together into one Grok experience, so there’s one place to create, build and get work done — xAI (X)
  2. Grok Build reportedly left 35,000 apps accessible, exposing user and company data — The Verge AI
  3. Musk Said Send Grok a Photo of Your Card. Would You Do It? — DEV Community — AI
  4. How does the LawVu MCP server work? — DEV Community — AI
  5. Two Grok Bots, One Software Factory: How My Lab Finds and Builds Its Own Work — DEV Community — AI
  6. GitHub Copilot Model Deprecations on Dec 14, 2026: What to Switch To — DEV Community — AI
  7. Grok Bot 1.0 just made AI teammates a LOT more useful. They can actually keep up with the whole office. Bring them into Slack, Microsoft Teams, or your meetings, and they can follow conversations and remember decisions. The more your team works with the — Sam Altman (X)
  8. How to Track Brand Mentions in ChatGPT and Grok — DEV Community — AI

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