The AI terms that
actually matter.
Clear, technical definitions of 146 key concepts — written by AI engineers, not marketers.
Contextual Retrieval
Contextual Retrieval is a RAG indexing technique that prepends a short, model-generated description of where a chunk sits in its source document before that chunk is embedded and BM25-indexed. Introduced by Anthropic in September 2024, it cuts retrieval failures by 49 percent on its own and by 67 percent when paired with reranking.
Read definitionContinual Learning
Continual learning (also called lifelong learning) trains a single model on a sequence of tasks or data distributions over time, aiming to acquire new knowledge without catastrophically forgetting what it already learned, unlike standard training which assumes a fixed, i.i.d. dataset seen all at once.
Read definitionCorrective RAG (CRAG)
Corrective RAG (CRAG) inserts a lightweight evaluator between retrieval and generation that scores how well the retrieved documents actually answer the query, then routes the pipeline down one of three corrective paths: refine and keep, discard and fall back to a live web search, or both at once. It was introduced in a January 2024 paper and is now a standard node in agentic RAG graphs built with LangGraph and similar frameworks.
Read definitionCross-Encoder vs. Bi-Encoder
A bi-encoder encodes a query and a document separately into vectors compared by a fast distance metric, while a cross-encoder feeds the query and document into the model together so it can attend across both; the tradeoff between the two, speed and scale versus accuracy, shapes almost every retrieval and reranking pipeline.
Read definitionDeepSeek V4
DeepSeek V4 is an open-source Mixture-of-Experts model family released in April 2026, with the flagship V4-Pro reaching 1.6 trillion total parameters and matching closed-source frontier models on coding and reasoning benchmarks at a fraction of the inference cost.
Read definitionDense Retrieval vs. Sparse Retrieval
Dense retrieval finds documents by comparing learned vector embeddings for semantic similarity, while sparse retrieval finds documents by matching weighted terms (like BM25) in an inverted index; modern search and RAG systems increasingly fuse both rather than picking one.
Read definitiondGSLM (Dialogue Generative Spoken Language Model)
dGSLM is a full-duplex generative spoken language model that uses a Siamese dual-encoder architecture with cross-attention to model both sides of a spoken dialogue simultaneously, without any text in the loop.
Read definitionDiffusionGemma
An experimental, open weights multimodal model by Google DeepMind that utilizes discrete text diffusion instead of autoregression to generate 256 token blocks in parallel. This enables extreme inference speeds.
Read definitionDots (OpenAI Always-On Agents)
Dots are OpenAI's always-on personal agents, launched at DevDay on September 29, 2026 and powered by GPT-6 Astra. Each Dot runs on its own cloud computer and browser, connects to your apps, and keeps working toward standing goals in the background instead of waiting for a chat prompt.
Read definitionDouble-Blind AI Benchmarking
Double-blind AI benchmarking is an evaluation protocol in which the model developer never sees the test items and the benchmark operator never sees the model weights. It is designed to defeat test-set contamination and benchmark overfitting at the same time, and in August 2026 MLCommons, Google DeepMind, OpenMined, and AVERI ran the first cryptographically enforced instance of it on a proprietary model.
Read definitionE-E-A-T (Experience, Expertise, Authoritativeness, Trustworthiness)
E-E-A-T is the four-factor framework in Google's Search Quality Rater Guidelines that human raters use to judge content and creator quality, with Trust as the load-bearing factor, and it has become a proxy signal that AI Overviews and other generative search engines lean on when deciding which sources to cite.
Read definitionEmbeddings
Embeddings are dense numerical vectors that represent the meaning of text, images, or other data in a high-dimensional space — where items that are semantically similar end up geometrically close together, enabling AI systems to measure meaning rather than just match keywords.
Read definitionStay ahead of the curve
Weekly newsletter on agentic AI, LLMs, and what we're building at Superteams — straight to your inbox.
Ready to ship AI in production?
We deploy fractional AI teams that deliver production-grade systems in 30–90 days. No fluff, no obligation.