LLM (Large Language Model)
A large language model is a neural network trained on massive text corpora—often trillions of tokens—to predict the next word in a sequence. That simple objective, scaled up, produces systems that can write code, summarize legal briefs, translate languages, and hold surprisingly coherent conversations. GPT-4, Claude, Gemini, and Llama are all LLMs. The "large" refers to parameter count, typically in the billions, which correlates loosely with capability but tightly with compute cost. LLMs are general-purpose by default and useless for specific tasks until you shape their behavior through prompting, fine-tuning, or connecting them to your data. The model is the engine. Everything else—retrieval, guardrails, UI, evaluation—is what makes it drive straight.
Related terms:
Gravity Wells
Gravity wells describe economic dynamics where scarce resources flow disproportionately to entities with the greatest ability to pay and deploy, creating self-reinforcing concentrations of power. In the AI economy, they form around critical bottlenecks in compute, power, and talent, determining who captures resources and who scrambles for scraps.
Token
In large language models, a token is the basic unit of text—usually chunks of three to four characters—that the model reads and generates. Since API costs, context windows, and rate limits are all measured in tokens, understanding tokenization is essential for controlling prompt length, cost, and model behavior.
Few-Shot Prompting
Few-shot prompting leverages AI’s pattern recognition by providing a handful of examples in the prompt, enabling the model to identify patterns and generate responses that match your intended style or format. This real-time approach achieves consistent, domain-specific outputs without needing massive datasets or model fine-tuning.