Every AI, email, and agent term explained for developers. From context engineering to DKIM.
Filter by category
AI systems that can autonomously plan, make decisions, and take actions to accomplish goals with minimal human intervention.
Low-quality, mass-produced AI-generated content that adds noise without providing genuine value.
A neural network component that lets a model dynamically focus on the most relevant parts of its input when producing each part of the output.
Standardized tests used to measure and compare AI model performance across specific tasks like reasoning, coding, math, and language understanding.
The discipline of designing and managing everything that flows into an AI model's context window — not just the prompt, but instructions, state, tool definitions, memory, and output constraints.
The maximum amount of text a language model can process in a single request, measured in tokens.
A technique where a smaller 'student' model is trained to replicate the behavior of a larger 'teacher' model, producing a compact model that retains much of the original's capability.
Numerical vector representations of text, images, or other data that capture semantic meaning, enabling similarity search and machine learning tasks.
The process of further training a pre-trained AI model on a specific dataset to specialize its behavior for a particular task.
When an AI model generates confident-sounding information that is factually incorrect or entirely fabricated.
The process of running input data through a trained AI model to get a prediction or output. Every API call to an LLM is an inference request.
Low-Rank Adaptation — a fine-tuning technique that trains a small set of additional parameters instead of modifying the entire model, making customization fast and memory-efficient.
A model architecture that uses a routing mechanism to activate only a subset of specialized sub-networks (experts) for each input, increasing capacity without proportionally increasing compute.
An attack where malicious input tricks an AI model into ignoring its instructions and performing unintended actions.
A technique that reduces the precision of a model's numerical weights to shrink its size and speed up inference, with minimal loss in quality.
A technique that improves AI responses by retrieving relevant documents and including them as context before generating an answer.
Reinforcement Learning from Human Feedback — a training technique where human preferences are used to fine-tune an AI model's behavior, making it more helpful, harmless, and honest.
AI model responses formatted in a predictable schema like JSON, enabling reliable machine-to-machine communication.
A parameter that controls the randomness of an LLM's output, where lower values produce more predictable responses and higher values produce more creative ones.
The basic units of text that language models read and generate, roughly equivalent to three-quarters of a word.
The ability of an AI model to call external functions, APIs, or services to take actions and retrieve real-time information.
The neural network architecture behind all modern LLMs, using self-attention to process sequences of tokens in parallel rather than one at a time.
A database optimized for storing, indexing, and querying high-dimensional vectors, commonly used to power semantic search and RAG in AI applications.
A development approach where programmers describe what they want in natural language and let AI generate the code.