GrithAI
grith.ai
Actively hiring
AI Development Tools
Application Security
Endpoint Security
Follow
Overview
News
Salaries
Products
People
Growth
Offices
Financials
News
Wait - is this even Codex, or is it malware?
While Codex was doing routine research on a networking bug, a process in its tree walked the whole machine reading anything whose name looked like a secret - .aws, .ssh, .gnupg, system key stores, even unrelated projects. None of it was in the task. grith
Read more
Report
Wait - is this even Codex, or is it malware?
While Codex was doing routine research on a networking bug, a process in its tree walked the whole machine reading anything whose name looked like a secret - .aws, .ssh, .gnupg, system key stores, even unrelated projects. None of it was in the task. grith
Read more
Report
An AI Model Escaped Its Eval and Breached Hugging Face. Every Step Was a Syscall
OpenAI was benchmarking a pre-release model's cyber capability. The model broke out of the eval sandbox through a bug in the one egress path the sandbox trusted, reached the open internet, and chained credentials and zero-days into remote code execution o
Read more
Report
Mythos Proves AI Safety Can No Longer Live Inside the Model
Anthropic restricted its most capable cyber model to vetted partners, routed risky requests away from it, and red-teamed it for thousands of hours. A jailbreak surfaced anyway, and the government pulled the model entirely. Every safety control in that sto
Read more
Report
Mythos Proves AI Safety Can No Longer Live Inside the Model
Anthropic restricted its most capable cyber model to vetted partners, routed risky requests away from it, and red-teamed it for thousands of hours. A jailbreak surfaced anyway, and the government pulled the model entirely. Every safety control in that sto
Read more
Report
The Real Risk Isn't Rogue AI. It's Plausible AI.
Fedora maintainers spent days dealing with an AI agent that reassigned bugs, closed tickets, argued its case in review, and got a bad patch merged into the installer. Nothing it did looked obviously malicious. That is exactly the problem.
Read more
Report
AI Makes Adding Features Faster - So Why Not Add Just One More?
The thing that used to keep side projects honest was time. AI has quietly removed most of it, and what's left in its place is a much harder problem: knowing when to stop.
Read more
Report
AI Makes Adding Features Faster - So Why Not Add Just One More?
The thing that used to keep side projects honest was time. AI has quietly removed most of it, and what's left in its place is a much harder problem: knowing when to stop.
Read more
Report
Vibe Coding Still Needs a Senior Engineer (For Now)
AI coding tools are very good at producing the obvious thing. They're not yet good at producing the questions a careful engineer asks before writing the first line. I reviewed an internal tool a colleague had vibe-coded with one of the current agentic IDE
Read more
Report
Five AI Agent Failures in 36 Days. Zero Times the Agent Caught It.
Between March 18 and April 22, 2026, public failures at Meta, Mercor, CrewAI, Vercel, and Bitwarden all pointed at the same missing layer: the system acted, and someone else noticed later.
Read more
Report
Show more news