29 articles
Series Fine-tuning ELYZA 8B and LLM-jp 7.2B for stock price prediction on Google Colab, the accuracy challenges encountered, and why I ultimately pivoted to the OpenAI API.
Series A detailed look at how I designed training data for stock price prediction, integrating company information, news, stock prices, financials, and macroeconomic indicators into a structured JSON format for LLM fine-tuning.
Series How choosing DeepSeek as a translation provider based on cost alone led to Chinese text leakage, latency issues, and data exposure -- and why I unified everything under ChatGPT.
Series How pivoting to OpenAI API fine-tuning on gpt-4o-mini achieved stable JSON output and sufficient accuracy in just 8 minutes, after months of struggle with open-source models.
Series The challenges of migrating from MySQL to Firestore for a production web service, including index design, upsert strategies, document ID design, and cost optimization for the Senrigan stock prediction platform.
Series Implementation notes on adding text-to-speech to the translation pipeline: Web Speech API code, mobile browser workarounds, Bluetooth audio routing, and the browser limitations that led toward a native app.
Series Local LLM inference on RTX 3060: Ollama setup and VRAM crash, LM Studio 0.4.0 headless CLI, lock mechanisms for parallel requests, mobile LLM feasibility research, and a guide for adapting to any language pair.
Series The core implementation: dual prompts for speed vs quality, streaming JSON extraction, debounce logic, and progressive frontend display — with full code.
Series Why existing voice translators break conversation flow, and how to set up the foundation for a real-time translator with Deepgram, FastAPI, and WebSocket.