| | Mythos Proves AI Safety Can No Longer Live Inside the Model (grith.ai) |
| 2 points by edf13 22 hours ago | past | discuss |
|
| | Mythos Proves AI Safety Can No Longer Live Inside the Model (grith.ai) |
| 3 points by edf13 2 days ago | past | discuss |
|
| | The Risk Isn't Rogue AI. It's Plausible AI (grith.ai) |
| 2 points by edf13 4 days ago | past | discuss |
|
| | AI Makes Adding Features Faster – So Why Not Add Just One More? (grith.ai) |
| 3 points by edf13 22 days ago | past | 2 comments |
|
| | AI Makes Adding Features Faster – So Why Not Add Just One More? (grith.ai) |
| 2 points by edf13 27 days ago | past |
|
| | Vibe Coding Still Needs a Senior Engineer (For Now) (grith.ai) |
| 5 points by edf13 35 days ago | past | 1 comment |
|
| | Five AI Agent Failures in 36 Days. Zero Times the Agent Caught It (grith.ai) |
| 3 points by edf13 48 days ago | past | 1 comment |
|
| | The Vercel Breach Needed Malware. The Next One Needs a Bad Readme (grith.ai) |
| 1 point by edf13 56 days ago | past | 3 comments |
|
| | Every Claude 4.7 Improvement Makes the Security Problem Worse (grith.ai) |
| 5 points by edf13 60 days ago | past | 1 comment |
|
| | They Hacked Claude, Gemini, and Copilot (and No One Told You) (grith.ai) |
| 4 points by edf13 60 days ago | past |
|
| | They Hacked Claude, Gemini, and Copilot (and No One Told You) (grith.ai) |
| 3 points by edf13 61 days ago | past |
|
| | Prompt Injection Is Unfixable (So We Stopped Trying) (grith.ai) |
| 4 points by edf13 62 days ago | past | 1 comment |
|
| | If Your AI Agent Ran NPM Install During the Axios Attack, You're Compromised (grith.ai) |
| 5 points by edf13 76 days ago | past |
|
| | Zero Ambient Authority: The Principle That Should Govern Every AI Agent (grith.ai) |
| 3 points by edf13 77 days ago | past |
|
| | Alibaba's AI Agent Hijacked GPUs and Dug Reverse SSH Tunnels (grith.ai) |
| 3 points by edf13 80 days ago | past |
|
| | AI agents are now deciding what's safe to run (Claude Auto Mode) (grith.ai) |
| 3 points by edf13 82 days ago | past |
|
| | The Trivy Supply Chain Attack Reached LiteLLM (grith.ai) |
| 3 points by edf13 83 days ago | past | 1 comment |
|
| | Meta's Rogue AI Agent Gave Engineers Access They Shouldn't Have Had (grith.ai) |
| 1 point by edf13 83 days ago | past |
|
| | Meta's Rogue AI Agent Gave Engineers Access They Shouldn't Have Had (grith.ai) |
| 3 points by edf13 83 days ago | past |
|
| | Google's A2A Protocol Has Zero Defenses Against Prompt Injection (grith.ai) |
| 4 points by edf13 87 days ago | past | 1 comment |
|
| | Permission Fatigue Is Not a UX Problem. It Is a Security Failure (grith.ai) |
| 3 points by edf13 88 days ago | past | 1 comment |
|
| | NemoClaw vs. Grith: Sandbox for One Agent vs. Security for All (grith.ai) |
| 3 points by edf13 89 days ago | past |
|
| | AI Agent Backdoors Trivy Security Scanner, Weaponizes a VS Code Extension (grith.ai) |
| 2 points by edf13 89 days ago | past |
|
| | AI Agent Backdoors Trivy Security Scanner, Weaponizes a VS Code Extension (grith.ai) |
| 2 points by edf13 89 days ago | past | 1 comment |
|
| | 87% of AI-Generated Pull Requests Ship Security Vulnerabilities (grith.ai) |
| 6 points by edf13 3 months ago | past |
|
| | Claude Code Auto Mode Lets the Agent Approve Its Actions – That's the Problem (grith.ai) |
| 3 points by edf13 3 months ago | past |
|
| | Claude Code Attempted 752 /proc/*/environ Reads. 256 Succeeded. Codex: 0 (grith.ai) |
| 4 points by edf13 3 months ago | past |
|
| | Claude Code Attempted 752 /proc/*/environ Reads. 256 Succeeded. Codex: 0 (grith.ai) |
| 3 points by edf13 3 months ago | past |
|
| | Grith (grith.ai) |
| 1 point by handfuloflight 3 months ago | past |
|
| | A GitHub Issue Title Compromised 4k Developer Machines (grith.ai) |
| 632 points by edf13 3 months ago | past | 195 comments |
|
|
| More |
