// LATEST
Cybersecurity
vulnx: Query 250,000+ CVEs Like You're Searching Your Email
Developer Tools
jqp: Building a Real-Time jq Playground with Go and Bubbletea
Cybersecurity
PyRIT: Microsoft's Framework for Red Teaming AI Systems Before They Fail in Production
LLM Engineering
Medusa: How Multiple Prediction Heads Eliminate the Draft Model Problem in LLM Inference
AI Dev Tools
Promptmap: Automated Security Testing for Your Custom LLM Applications
Automation
Untangle: Multi-Layer Web Server Fingerprinting for Modern Infrastructure
AI Agents
ZenGuard: The Fast Trust Layer for AI Agents That Got Archived Too Soon
Cybersecurity
Navigating the Dark Side of Foundation Models: A Security Research Compendium
Developer Tools
Inside METR's Public Tasks: How AI Safety Researchers Test for Dangerous Agent Capabilities
AI Agents
TruLens: Building Observability Into Your RAG Pipeline Before Production Bites You
Developer Tools
Inside the Repository Tracking How Threat Actors Actually Use AI (Spoiler: It's Mostly Phishing)
Cybersecurity
Building a Secret Scanning Arsenal: Inside GitHub's Custom Pattern Library
Cybersecurity
CVE-2024-22026: How Unsigned RPM Installation Becomes Root-Level Compromise
AI Dev Tools
PII Detective: Finding Sensitive Data by Reading the Room (Not the Records)
Developer Tools
Building Shazam from Scratch: Inside SeekTune's Audio Fingerprinting Pipeline
Cybersecurity
Kraken: The Security Testing Menu That Consolidates 18 Attack Vectors Into One CLI
AI Agents
Vivaria: Inside METR's Agent Evaluation Platform Before the Migration to Inspect AI
Developer Tools
PIGEON: How CLIP Embeddings Predict GPS Coordinates from Photos (And Why the Code Won't Help You Build It)
AI Dev Tools
Dotai: Engineering AI Context as Infrastructure for Claude and Cursor
LLM Engineering
Building RAG Systems From First Principles: A Workshop Teardown
LLM Engineering
Building a Privacy-First File Organizer with On-Device AI Models
AI Dev Tools
o1-engineer: Teaching OpenAI's Reasoning Model to Write Your Codebase
LLM Engineering
MLX-VLM: Running Vision Language Models Locally on Apple Silicon Without the CUDA Tax
Developer Tools