ai
7 articles in this category.
Large Language Model A neural network trained on massive text corpora to generate and understand natural language, forming the foundation of modern AI assistants. AI Agent An LLM-powered system that can perceive its environment, reason about goals, and take actions through tools — going beyond single-prompt generation. Retrieval-Augmented Generation A technique that grounds LLM outputs in external knowledge by retrieving relevant documents at query time, reducing hallucination and extending the model's knowledge. Context Window The maximum amount of text a language model can process in a single inference call, measured in tokens — the fundamental memory limit of an LLM. Transformer The neural network architecture that revolutionized NLP through self-attention, enabling parallel sequence processing and forming the basis of all modern LLMs. Embedding A dense vector representation of data (text, images, audio) in a continuous space where semantic similarity corresponds to geometric proximity. Attention Is All You Need (Vaswani et al. 2017) Paper seminal yang memperkenalkan arsitektur Transformer — paper paling penting di AI modern.