Starlog — Page 48
// LATEST
LLM Engineering
OWASP's Open Asset Model: Treating Your Attack Surface Like a Knowledge Graph
LLM Engineering
DeepEval: Testing LLM Applications Like You Test Your Code
AI Dev Tools
Outlines: Why Constraining Tokens Beats Parsing JSON from LLMs
LLM Engineering
Training Custom LLMs with Synthetic Data: How GPT-4 Can Build Your Dataset
Data & Knowledge
The 6,400-Star GitHub Repository That's Actually a Privacy To-Do List
LLM Engineering
Axflow: A Zero-Dependency TypeScript Framework That Treats AI Like First-Class Infrastructure
Data & Knowledge
Flower: Building Federated Learning Systems Without Reinventing Privacy Infrastructure
Developer Tools
LunaPipe: Bringing ChatGPT into the Unix Pipeline
AI Agents
n8n: Building Self-Hosted Workflow Automation That Doesn't Lock You In
Infrastructure
Inside Chip Huyen's ML Systems Design Philosophy: What 5,000 Stars Tell Us About Production ML
Developer Tools
Building a JavaScript Surveillance System: Inside FileChangeMonitor's Architecture
AI Dev Tools
SmartGPT's Dual-Agent Architecture: Why Separating Reasoning from Execution Matters
Developer Tools
Ratatui: How Rust's Fastest-Growing TUI Library Uses Immediate-Mode Rendering and Smart Diffing
AI Dev Tools
Inside AutomatedLLMAttacker: A Bare-Bones Prompt Injection Testing Framework
Automation
Keep: Building an Open-Source AIOps Platform That Actually Reduces Alert Fatigue
Developer Tools
Humanify: Using LLMs to Deobfuscate JavaScript Without Hallucination Risks
Developer Tools
Building an Auto-OCR Pipeline for Notion: A Deep Dive into notion-auto-ocr
Cybersecurity
Inside the Adversarial Robustness Toolbox: Building ML Systems That Survive Attacks
Developer Tools
Mods: Bringing LLMs into Your Unix Pipeline Before It Disappears
Developer Tools
Open Interpreter: Turning ChatGPT Into a Local Code Execution Engine
AI Agents
MetaGPT: Building Software Companies from Prompts with Multi-Agent SOPs
Cybersecurity
Promptfoo: The Open-Source LLM Security Scanner That OpenAI and Anthropic Actually Use
LLM Engineering
LLM Guard: Building a Security Middleware Layer for Large Language Models
AI Dev Tools