EXPLORE / 06
Terms index
Specialized AI and software-development terms with concise explanations
RECORDS
Entity records
3367 records · 36/85
- 1401
Hidden Information
Key variables affecting outcomes that are not directly observable during decision-making.
Website pending - 1402
Imperfect Information Game
A game where players lack full knowledge of opponents' states or private information.
Website pending - 1403
Web Scraping
Automated extraction of data from web pages by software programs
Website pending - 1404
AI Overviews
Direct answer summaries generated by large models within Google Search
Website pending - 1405
Memory Bandwidth Bottleneck
System performance limitation caused by data transfer speed constraints
Website pending - 1406
Export Control
Government policies restricting the cross-border flow of specific technologies or products.
Website pending - 1407
A100/H100
Nvidia's data center GPUs designed for high-performance computing and AI model training.
Website pending - 1408
Full-Disk Access
A high-level permission allowing an app to read and write all files on the system
Website pending - 1409
Transformer Encoder
Core neural network module processing sequences via self-attention mechanisms
Website pending - 1410
LLM Engineering
Software engineering practices for designing, deploying, and optimizing LLM applications.
Website pending - 1411
Semantic Security
Content-meaning-based filtering preventing attacks like prompt injection, unlike keyword matching
Website pending - 1412
TensorFlow
An end-to-end open source machine learning platform developed by Google
Website pending - 1413
DDP
A training strategy that shards data across devices for parallel gradient computation and synchronization
Website pending - 1414
GPT Architecture
An autoregressive generative model structure based on stacked Transformer decoders.
Website pending - 1415
Face Swapping
Technology that transfers facial features from a source person to a target in video.
Website pending - 1416
Agent Framework
Software architecture supporting LLMs in autonomous planning, tool calling, and task execution
Website pending - 1417
Spec
Detailed documentation describing software functionality, behavior, or constraints, often used to guide AI code generation.
Website pending - 1418
Call Chain / Trace
A data structure recording all service nodes and interaction sequences a request passes through in a distributed system.
Website pending - 1419
Agent Observability
The capability to monitor and analyze an AI agent's decision paths, tool calls, and resource consumption.
Website pending - 1420
End-to-End Delivery
A mode where the entire process from requirement analysis to final product deployment is automated or completed as a unified whole.
Website pending - 1421
Runtime Sovereignty
Judgment and control over the AI execution environment, state management, and ultimate authority ownership.
Website pending - 1422
Mental Model
The internal cognitive structure developers use to predict system behavior and guide debugging.
Website pending - 1423
3D World Building
The process of creating 3D virtual environments and objects using algorithms or tools
Website pending - 1424
Object Storage
A data storage architecture that manages data as objects, suitable for large-scale access to unstructured data.
Website pending - 1425
Hot-swapping
Technique allowing dynamic loading or unloading of components without restarting the system
Website pending - 1426
Plugin Architecture
A design pattern allowing dynamic system extension via independent modules without modifying core code.
Website pending - 1427
Cross-platform Development
Building apps for multiple OSes from a single codebase.
Website pending - 1428
Over-engineering
Designing a solution to be more complex than necessary for the problem at hand
Website pending - 1429
ReAct
An agent framework combining Reasoning and Acting to enhance model decision-making capabilities
Website pending - 1430
Multi-head Latent Attention (MLA)
An attention mechanism that compresses KV cache via low-rank projection to reduce memory usage and computation.
Website pending - 1431
MLA
An attention variant that compresses key-value pairs to reduce memory usage and computation
Website pending - 1432
Regression Evaluation
Testing system changes against historical cases to ensure no performance degradation.
Website pending - 1433
Full-duplex Voice Interaction
A dialogue mode allowing users to speak simultaneously with AI and interrupt at any time
Website pending - 1434
End-to-End Voice Dialogue
Generating audio responses directly from audio input without intermediate text conversion
Website pending - 1435
N-gram Embedding
A method using continuous word sequences for lookup addressing to enhance memory efficiency.
Website pending - 1436
Model-as-a-Service
A business model delivering AI model capabilities via cloud APIs for developers.
Website pending - 1437
Distributed System
A system architecture where multiple computers collaborate over a network to complete common tasks.
Website pending - 1438
Pareto Frontier
A set of optimal solutions where improving one objective (e.g., performance) requires sacrificing another (e.g., cost)
Website pending - 1439
Graph Structure
A data structure of nodes and edges representing entity relationships
Website pending - 1440
Inverted Index
A classic data structure mapping terms to documents for fast full-text retrieval.
Website pending