From PDF to Data: A Practical Guide to marker and LLMs
Learn how to extract structured data from PDFs using marker and LLMs. A practical guide to building cost-effective document processing pipelines with Claude, Gemini, and local models.
Software Thug
Essential Homebrew Packages: My Favorite Terminal Tools for macOS
A curated collection of essential Homebrew packages for macOS power users. From terminal file managers to video processing tools, these are the packages I install on every new system.
OpenSpec vs Spec Kit vs Agent OS: Choosing the Right Spec-Driven Development Framework
A comprehensive comparison of three spec-driven development frameworks—OpenSpec, GitHub Spec Kit, and Agent OS—including pros, cons, and when to use each for AI-assisted coding.
LLM Benchmarks Explained: From Needle in a Haystack to SWE-bench
A complete guide to understanding how LLMs are tested. Learn what Needle in a Haystack, BrowseComp, Oolong, LongBench v2, MMLU, SWE-bench, and other benchmarks actually measure—and why it matters.
Claude Code MCP Tool Search: How Lazy Loading Cut Token Usage by 85%
Claude Code 2.1.7 introduced MCP Tool Search, a lazy loading mechanism that reduces token consumption by 85% and improves model accuracy significantly. Here's how it works and what it means for your workflows.
Claude Code Extension Mechanisms: Skills, Agents, MCP, and Slash Commands Compared
A comprehensive comparison of Claude Code's four extension mechanisms—slash commands, MCP servers, skills, and subagents—including context impact, interaction patterns, and when to use each.
Scheduling Claude Code Agents and Skills: Converting n8n Workflows to AI-Powered Automation
If you’re coming from n8n or other workflow automation tools, you might be wondering how to schedule Claude Code agents or skills to run automatically. While Claude Code doesn’t have built-in sched...
Realtime Models vs STT-LLM-TTS Pipeline: Choosing the Right Architecture for Voice AI
A comprehensive comparison of speech-to-speech realtime models versus the traditional STT→LLM→TTS pipeline for building voice AI applications with LiveKit.
The Complete Guide to LiveKit Voice AI: STT, TTS, LLM & Realtime Models Compared
A comprehensive comparison of all Speech-to-Text, Text-to-Speech, LLM, and Realtime model options available in LiveKit Agents, including pricing, pros/cons, and recommendations.
Welcome to Software Thug
Welcome to my corner of the internet. This is where I’ll be sharing my thoughts on software development, interesting projects, and lessons learned along the way. What to Expect Here’s what you ca...