Series
Multi-part deep dives into AI engineering projects, from concept to production.
Migrating a virtual try-on system from PASTA-GAN++ to Gemini and Vertex AI — replacing an entire GPU pipeline with API calls and resolving the body diversity problem that GANs could never solve.
Building an ML-powered meal planning system to solve the daily struggle of nutritious, varied cooking — from cosine similarity to LSTM to ChatGPT.
Building a browser-based investment education game for children — from board game concept to Next.js + Phaser 3 production app with real Japanese economic history.
Building a GAN-based virtual try-on system — from surveying 15+ VTON models and pose estimation to full-body garment transfer and smartphone app design.
Building an AI stock prediction service that reads corporate news and predicts next-day price movements using fine-tuned LLMs.
A practical guide to building a near real-time voice translator using streaming LLM, Deepgram, and WebSocket — with full code examples.