Matt Mickiewicz
Matt is the co-founder of SitePoint, 99designs and Flippa. He lives in Vancouver, Canada.
Matt Mickiewicz's articles
Cursor Origin: GitHub Sync and Code Hosting Setup in Early Beta
Matt Mickiewicz
Codex CLI: OpenAI's Open Agent Harness — Installation, Commands, and CI Integration
Matt Mickiewicz
Claude Opus 5 Is Most Efficient at Medium Effort: FrontierCode Benchmark Data Explained
Matt Mickiewicz
Alibaba Bans Claude Code: The Backdoor Scare Explained
Matt Mickiewicz
The Cost Inversion: Running Production AI on DeepSeek V4-Flash vs Gemini
Matt Mickiewicz
OpenClaude with DeepSeek V4: Running a Fully Private AI Coding Engine on Your Laptop
Matt Mickiewicz
headroom: The Token-Compression CLI That Cuts Your LLM API Costs by 60–95%
Matt Mickiewicz
The New Reality of Agent Memory: The Complete Guide (2026)
Matt Mickiewicz
Audio-Visual Vibe Coding with Qwen3.5-Omni: Write Code from Video Alone
Matt Mickiewicz
DeepSeek API Integration with React and Next.js
Matt Mickiewicz
Claude Code 2.5: New Features for Web Developers
Matt Mickiewicz
Chain-of-Thought Debugging with DeepSeek-R1: When to Let AI Think Through Bugs
Matt Mickiewicz
Integrating DeepSeek-R1 with VS Code: HTTP API Extension Development
Matt Mickiewicz
How to Use GPT-5.4 Computer Use API with OpenClaw: Complete Guide
Matt Mickiewicz
GPT-5.4 Mini vs GPT-4o Mini: The Complete 2026 Developer Comparison
Matt Mickiewicz
Why GPT-5.4 Mini is a Game Changer for Voice AI Applications
Matt Mickiewicz
Context Management for Long-Running Claude Code Sessions
Matt Mickiewicz
Seedance 2.0 vs. Sora 2 vs. Runway Gen-4: AI Video API Comparison for Developers (2026)
Matt Mickiewicz
GGML Joins Hugging Face: What This Means for Local Model Optimization
Matt Mickiewicz
OpenClaw in Production: Lessons from 4 Weeks of Self-Hosted AI Agents
Matt Mickiewicz
OpenAI's New Agentic Primitives: A Beginner's Guide to Skills, Hosted Shell, and Server-Side Compaction
Matt Mickiewicz
Beyond Chat: How to Set Up Local LLM Code Completion in VS Code with Ollama
Matt Mickiewicz
Why WebGPU is the Future of Browser-Based AI (No Python Required)
Matt Mickiewicz
The Definitive Guide to Local LLMs in 2026: Privacy, Tools, & Hardware
Matt Mickiewicz
Ollama vs. vLLM: When to Start Scaling Your Local AI Stack
Matt Mickiewicz
VRAM Poverty Line: Why 16GB Is the Minimum GPU for Running 70B Models in 2026
Matt Mickiewicz
The Small Data Revolution: Why You Don't Need RAG for 1M Token Windows
Matt Mickiewicz
Beyond Chat: How to Set Up Local LLM Code Completion in VS Code (Without Copilot)
Matt Mickiewicz
Why WebGPU Is the Future of Browser-Based AI (No Python Required)
Matt Mickiewicz
React 19 Compiler vs. Svelte 5: The Virtual DOM Latency Benchmark
Matt Mickiewicz
How to Get Started with Amazon’s Simple Notification Service
Matt Mickiewicz
A Guide to the Most Useful AWS EKS Commands
Matt Mickiewicz
Showing 32 of 71