Hacker Newsnew | past | comments | ask | show | jobs | submit | edf13's submissionslogin
1.
 [flagged] Show HN: ClaudeStatsBar: your session is 486k deep and nothing told you (github.com/field-logic-ltd)
18 points by edf13 13 days ago | past | 15 comments
2.
A Git Config Key Ran Code in Seven Coding Agents. The 2022 Fix Does Not Stop It (grith.ai)
4 points by edf13 15 days ago | past
3.
Show HN: Grith – syscall-level supervision for AI agents (github.com/grith-ai)
3 points by edf13 16 days ago | past | 1 comment
4.
An agent skill can hand a stranger your shell – hours after you installed it (grith.ai)
3 points by edf13 17 days ago | past
5.
98% of What Claude Code Does, I Never See. The 0.27% It Stops for Is the Point (grith.ai)
1 point by edf13 20 days ago | past
6.
73% of What We Blocked in a Month Was One Syscall Your Sandbox Cannot See (grith.ai)
3 points by edf13 20 days ago | past
7.
Grith is live – security proxy for AI coding agents (grith.ai)
4 points by edf13 27 days ago | past | 1 comment
8.
Show HN: Grith – syscall-level supervision for AI coding agents on Linux (github.com/grith-ai)
4 points by edf13 27 days ago | past
9.
Wait – is this even Codex, or is it malware? (grith.ai)
2 points by edf13 62 days ago | past
10.
Codex swept my whole disk for credentials. grith froze every real one (grith.ai)
5 points by edf13 62 days ago | past
11.
An AI Model Escaped Its Eval and Breached Hugging Face. Every Step Was a Syscall (grith.ai)
4 points by edf13 64 days ago | past
12.
Mythos Proves AI Safety Can No Longer Live Inside the Model (grith.ai)
2 points by edf13 3 months ago | past
13.
Mythos Proves AI Safety Can No Longer Live Inside the Model (grith.ai)
3 points by edf13 3 months ago | past
14.
The Risk Isn't Rogue AI. It's Plausible AI (grith.ai)
2 points by edf13 3 months ago | past
15.
AI Makes Adding Features Faster – So Why Not Add Just One More? (grith.ai)
3 points by edf13 4 months ago | past | 2 comments
16.
AI Makes Adding Features Faster – So Why Not Add Just One More? (grith.ai)
2 points by edf13 4 months ago | past
17.
Vibe Coding Still Needs a Senior Engineer (For Now) (grith.ai)
5 points by edf13 4 months ago | past | 1 comment
18.
Five AI Agent Failures in 36 Days. Zero Times the Agent Caught It (grith.ai)
3 points by edf13 4 months ago | past | 1 comment
19.
The Vercel Breach Needed Malware. The Next One Needs a Bad Readme (grith.ai)
1 point by edf13 5 months ago | past | 3 comments
20.
Every Claude 4.7 Improvement Makes the Security Problem Worse (grith.ai)
5 points by edf13 5 months ago | past | 1 comment
21.
They Hacked Claude, Gemini, and Copilot (and No One Told You) (grith.ai)
4 points by edf13 5 months ago | past
22.
They Hacked Claude, Gemini, and Copilot (and No One Told You) (grith.ai)
3 points by edf13 5 months ago | past
23.
Prompt Injection Is Unfixable (So We Stopped Trying) (grith.ai)
4 points by edf13 5 months ago | past | 1 comment
24.
If Your AI Agent Ran NPM Install During the Axios Attack, You're Compromised (grith.ai)
5 points by edf13 5 months ago | past
25.
Zero Ambient Authority: The Principle That Should Govern Every AI Agent (grith.ai)
3 points by edf13 5 months ago | past
26.
Alibaba's AI Agent Hijacked GPUs and Dug Reverse SSH Tunnels (grith.ai)
3 points by edf13 6 months ago | past
27.
Claude now decides what's safe to run – a UX improvement, not a security fix (twitter.com/grithai)
3 points by edf13 6 months ago | past
28.
AI agents are now deciding what's safe to run (Claude Auto Mode) (grith.ai)
3 points by edf13 6 months ago | past
29.
The Trivy Supply Chain Attack Reached LiteLLM (grith.ai)
3 points by edf13 6 months ago | past | 1 comment
30.
Meta's Rogue AI Agent Gave Engineers Access They Shouldn't Have Had (grith.ai)
1 point by edf13 6 months ago | past

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: