Starlog — Page 5
// LATEST
LLM Engineering
Running a 2.78-Trillion-Parameter Model on a Laptop: Inside WASTE's NVMe-Streaming Engine
Cybersecurity
Blacksea: The Active Honeypot That Exploits LLM Agents to Hack Back
AI Agents
Mindwalk: Watching Your Coding Agent Wander Through a 3D Map of Your Codebase
Cybersecurity
StealthBench: The First Benchmark That Measures Whether AI Agents Hack Like Professionals or Script Kiddies
AI Agents
Agent Orchestrator: Git Worktrees Are the Secret to Running 23 AI Coding Agents in Parallel
Automation
Maxun: How LLM-Powered Web Scraping Fixes the Brittleness Problem
AI Dev Tools
Weco CLI: Tree Search for Code Optimization When Manual Iteration Isn't Enough
Cybersecurity
Deepsec: When Your Security Audit Needs to Think, Not Just Pattern Match
AI Agents
VulnHunter: How Capital One Built a Self-Falsifying AI Security Scanner
Developer Tools
Westworld: A Web Agent Benchmark That Solves Reproducibility by Simulating the Internet
Infrastructure
Teaching AI to Build AI: Google's agents-cli and the Meta-Tooling Revolution
AI Agents
Screenpipe: Building AI Agents That Remember What You Actually Did
AI Dev Tools
OmniRoute: How Aggressive Token Compression and Four-Tier Fallbacks Let You Code on 268 Free AI Providers
AI Agents
Building a Bill of Materials for AI Agent Skills: Inside skill-discovery's Cross-Platform Inventory Engine
Developer Tools
GrokPatrol: How to Build Forensic Tools That Can't Lie to You
AI Agents
Mantis: Google's 15-Stage Pipeline for Teaching AI Agents to Hunt Vulnerabilities
AI Agents
Cloudflare's Security Audit Skill: Teaching AI Agents to Red Team Your Code
Developer Tools
Natural Language Autoencoders: Reading Neural Activation Vectors as English Text
AI Agents
Building an MCP Server for Apple's TestFlight Feedback: Why JWT Caching Matters
LLM Engineering
Running 753B MoE Models on Consumer GPUs: Hand-Written SASS Kernels for 2-Bit Experts
AI Agents
Agentic Awesome Skills: The npm Registry That AI Coding Agents Actually Needed
Developer Tools
Watching Language Models Think: Real-Time Jacobian Lens Visualization with Subtext
AI Agents
Fable5: Engineering AI Agent Reliability Through Enforcement, Not Hope
Cybersecurity