Large Language Model (LLM), AI trained on huge amounts of text that predicts and generates language and code., Inference, The moment a trained model actually produces an output from your input., Token, The small chunk of text a model reads and writes., Context window, How much text the model can "hold in mind" at once., Prompt engineering, Crafting the instructions you give an AI to get a better result., Hallucination, When AI confidently produces something false or inverted., Agentic, AI that can act by itself, Non-deterministic, The same prompt can produce a different answer each time., Code completion, AI suggesting the next lines of code as you type., Scaffolding, Auto-generating the basic structure of a project to build on., Fine-tuning, Extra training that specialises a general model for a specific task., Abstraction, Hiding low-level detail so you can work at higher level., Codebase, The whole collection of source code that makes up a project., Repository, A storage space holding a project's code and its history., Refactoring, Restructuring existing code without changing what it does., Technical debt, The future cost of choosing a quick fix over a clean solution., Boilerplate, Repetitive, standard code you need just to get something running., Dependency, External code or a library your project relies on to work., Bloat, unnecessarily large or slow software due to poor optimization., Legacy Code, Old code that's hard to understand or change .

Vibecoding

Autor
Ispis
Postavi

Top-lista

Vizualni stil

Postavke

Promijeni predložak

Vrati automatski spremljeno: ?