How large language models and the systems around them actually work.
5 posts
ARC Prize says OpenAI's GPT-6 Astra scores 62.7% on ARC-AGI-3 with its standard harness and 99.9% with OpenAI's own memory settings. What the gap means.
When and how to fine-tune language models using LoRA, including dataset preparation and evaluation.
How to run open-source LLMs on your own hardware using Ollama, llama.cpp, and quantized models.
A step-by-step guide to building retrieval-augmented generation systems with vector databases.
A clear explanation of transformer architecture, attention mechanisms, and tokenization for developers.
