Category
Tools we use daily: setups, tricks and battle-tested automations.
With quantization, model weights are stored with fewer bits (4, 5, or 8 instead of 16), so Llama 2 13B shrinks from 26 GB to about 7.5 GB. With llama.cpp it runs on an ordinary 16GB-RAM laptop with no dedicated GPU, and the quality loss is smaller than intuition suggests.
ChatGPT plugins let the model invoke external services through an OpenAPI specification. Three months after launch, the ecosystem has around 500 plugins with a clear pattern: they work well for live data lookup and internal API exposure, but show friction in multi-plugin orchestration and real-money transactions.
GitHub Copilot is a coding assistant from GitHub and OpenAI that suggests code in real time inside the editor, trained on billions of lines of public code. It speeds up repetitive tasks such as tests, boilerplate, and documentation, but its suggestions always need human review before reaching production.
