AI & Machine LearningJune 24, 20268 min read
Fine-Tuning LLMs with LoRA: A Practical Guide for Small Teams
How to fine-tune open-source language models on a single GPU using LoRA and PEFT — the exact workflow I use to ship AI products at TechToTech.
The TechToTech Blog
Notes on AI, LLM fine-tuning, full-stack development, and what it actually takes to ship software as a solo studio.
Studio NotesJune 18, 20265 min read
Why Founder-Led Studios Ship Faster Than Agencies
Fewer handoffs, tighter feedback loops, and one person accountable end to end. Here's why a solo studio can outbuild a 20-person agency for many projects.
Backend & InfrastructureJune 10, 20267 min read
Supabase vs Firebase in 2026: Which One Should You Actually Use?
A pragmatic comparison from someone who ships production apps on both. Postgres, RLS, edge functions, pricing, and the parts nobody tells you about.
AI & Machine LearningJune 2, 20266 min read
Shipping AI Agents That Actually Work in Production
Most AI agent demos fall apart the moment a real user touches them. Here's the framework we use to build agents that survive contact with reality.
Business & StrategyMay 25, 20264 min read
Why Every Small Business in 2026 Needs a Technical Partner
AI, automation, and cloud tools are eating the market. Businesses without a technical partner are already falling behind — here's what to do about it.