Insight The Reality of 'Continual Learning' ― Can AI Truly Evolve on Its Own?
As many AI services claim 'continual learning' capabilities, here's how to distinguish genuine self-learning from glorified note-taking.
Read →
LLM
11 articles tagged with "LLM"
Insight 
Series Part 1: The Beginning and the Big Picture -- The Day ChatGPT Beat the Fund Managers
How an experiment where ChatGPT outperformed professional fund managers inspired me to build Senrigan, an AI stock price prediction service powered by a fine-tuned LLM.
Read →
Series Part 2: The Local GPU Challenge and Defeat -- Taking on an 8B Model with 6 GB of VRAM on the RTX 3060
My first attempt at fine-tuning ELYZA Llama-3-JP-8B on a local RTX 3060 GPU, and the hard lessons learned about VRAM limitations when training large language models.
Read →
Series Part 3: LoRA and Quantization Explained -- The Techniques That Make LLMs Lighter
A deep dive into LoRA, quantization, QLoRA, and SFTTrainer -- the key techniques that enable fine-tuning large language models on consumer hardware, validated through a Mount Fuji proof-of-concept experiment.
Read →
Series Part 4: Stock Prediction on Colab -- Trial and Error with Three Models
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.
Read →
Series Part 6: Training Data Design -- How I Integrated Five Types of Data
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.
Read →
Series Part 7: Choosing a Translation LLM -- From DeepSeek to ChatGPT
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.
Read →
Series Part 5: OpenAI API Fine-Tuning -- The Final Solution That Took Just 8 Minutes
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.
Read →
Series Part 3. Build Your Own Real-Time Translator - Ollama, LM Studio, and Home GPU
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.
Read →