The AI terms that
actually matter.
Clear, technical definitions of 148 key concepts — written by AI engineers, not marketers.
Rotary Positional Embedding (RoPE)
Rotary Positional Embedding (RoPE) is the positional encoding used by nearly every modern open-weight LLM: it rotates query and key vectors by an angle proportional to their sequence position, so the attention score between two tokens depends only on their relative distance, the property that makes post-training context-length extension (YaRN, NTK-aware scaling, LongRoPE) possible.
Read definitionRRF (Reciprocal Rank Fusion)
Reciprocal Rank Fusion is a simple, training-free algorithm for combining multiple ranked result lists — typically dense vector search and sparse keyword search — into a single, more accurate ranking, using only each item's rank position rather than its raw score.
Read definitionSeedance 2.0
Glossary about Seedance 2.0
Read definitionSeedream 5.0 Lite
Seedream 5.0 Lite is a multimodal image generation model on BytePlus ModelArk, supporting text and image inputs for high-quality, instruction-aligned image generation and editing workflows.
Read definitionSemantic Cache
Semantic cache is a caching technique where LLM responses are stored and retrieved based on semantic similarity between queries rather than exact string matching — dramatically reducing redundant LLM calls and API costs when users ask questions that mean the same thing in different words.
Read definitionSemantic Chunking
Semantic chunking splits a document into retrieval chunks at points where consecutive sentences stop being topically similar, using embedding-similarity drops or discourse boundaries instead of a fixed character or token count. It trades extra compute at ingest time for chunks that hold together as coherent units of meaning.
Read definitionSemantic Routing
An inference-serving layer that classifies each incoming prompt by intent and difficulty, then routes it to a cheap fast-path model or an expensive reasoning-enabled model accordingly, instead of applying the same reasoning budget to every request.
Read definitionShadow AI
Shadow AI is the use of AI tools, models, browser extensions, or personal AI accounts inside an organization without the knowledge, approval, or oversight of IT, security, legal, or compliance teams. It inherits every risk of classic shadow IT and adds AI-specific exposure: sensitive data pasted into public models, unreviewed agent actions, and regulatory obligations under frameworks like the EU AI Act.
Read definitionSHAP (SHapley Additive exPlanations)
SHAP is a method for explaining any machine learning prediction by assigning each input feature a signed contribution that adds up to the difference between that prediction and the model's average output. The contributions are Shapley values from cooperative game theory, which makes them the unique attribution satisfying a short list of fairness axioms.
Read definitionSliding Window Attention (SWA)
Sliding Window Attention (SWA) restricts each token to attending only within a fixed-size local neighborhood instead of the full sequence, cutting attention cost from quadratic to linear in sequence length; stacked across layers its effective receptive field still reaches far, and interleaving it with periodic full-attention layers (Mistral, Gemma, GPT-OSS) is the standard recipe modern LLMs use to control KV cache size at long context.
Read definitionSora AI Model
Sora is OpenAI's groundbreaking text-to-video AI model and can generate high-def videos of up to 1 min duration.
Read definitionSovereign AI
Sovereign AI refers to the strategic development, deployment, and control of artificial intelligence capabilities by a nation, region, or organization to ensure data privacy, security, and cultural alignment, independent of foreign or third-party infrastructure.
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.