HN Explorer

edf13

↗ HN profile [ 96.1 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Mythos Proves AI Safety Can No Longer Live Inside the Model (grith.ai)
    2 points 0
  2. Mythos Proves AI Safety Can No Longer Live Inside the Model (grith.ai)
    3 points 0
  3. The Risk Isn't Rogue AI. It's Plausible AI (grith.ai)
    2 points 0
  4. AI Makes Adding Features Faster – So Why Not Add Just One More? (grith.ai)
    3 points 1
  5. AI Makes Adding Features Faster – So Why Not Add Just One More? (grith.ai)
    2 points 0
  6. Vibe Coding Still Needs a Senior Engineer (For Now) (grith.ai)
    5 points 2
  7. Five AI Agent Failures in 36 Days. Zero Times the Agent Caught It (grith.ai)
    3 points 2
  8. The Vercel Breach Needed Malware. The Next One Needs a Bad Readme (grith.ai)
    1 points 1
  9. Every Claude 4.7 Improvement Makes the Security Problem Worse (grith.ai)
    5 points 1
  10. They Hacked Claude, Gemini, and Copilot (and No One Told You) (grith.ai)
    4 points 0
  11. They Hacked Claude, Gemini, and Copilot (and No One Told You) (grith.ai)
    3 points 0
  12. Prompt Injection Is Unfixable (So We Stopped Trying) (grith.ai)
    4 points 1
  13. If Your AI Agent Ran NPM Install During the Axios Attack, You're Compromised (grith.ai)
    5 points 2
  14. Zero Ambient Authority: The Principle That Should Govern Every AI Agent (grith.ai)
    3 points 1
  15. Alibaba's AI Agent Hijacked GPUs and Dug Reverse SSH Tunnels (grith.ai)
    3 points 0
  16. Claude now decides what's safe to run – a UX improvement, not a security fix (twitter.com)
    3 points 1
  17. AI agents are now deciding what's safe to run (Claude Auto Mode) (grith.ai)
    3 points 2
  18. The Trivy Supply Chain Attack Reached LiteLLM (grith.ai)
    3 points 1
  19. Meta's Rogue AI Agent Gave Engineers Access They Shouldn't Have Had (grith.ai)
    1 points 0
  20. Meta's Rogue AI Agent Gave Engineers Access They Shouldn't Have Had (grith.ai)
    3 points 1
  21. Google's A2A Protocol Has Zero Defenses Against Prompt Injection (grith.ai)
    4 points 3
  22. Claude Code Channels (twitter.com)
    2 points 1
  23. Permission Fatigue Is Not a UX Problem. It Is a Security Failure (grith.ai)
    3 points 1
  24. NemoClaw vs. Grith: Sandbox for One Agent vs. Security for All (grith.ai)
    3 points 1
  25. AI Agent Backdoors Trivy Security Scanner, Weaponizes a VS Code Extension (grith.ai)
    2 points 0