Artificial Intelligence (AI) Glossary
This 📝memo is a glossary of terms for all things related to 📝Artificial Intelligence (AI).
Glossary
A
- 📝Agents Managing Agents – Supervisory agents that spawn, monitor, and steer other agents.
- AI Agent – Autonomous system that plans, acts, and critiques to achieve goals.
- 📝Artificial General Intelligence (AGI) – Human-level AI that generalizes across domains.
- 📝Artificial Intelligence (AI) – Machines performing tasks requiring human intelligence.
- 📝Artificial Super Intelligence (ASI) – AI surpassing human capability in all domains.
B
- 📝Background Agents – Agents that run tasks asynchronously and report back when done.
- Benchmarks – Standard test sets for model performance (MMLU, GSM8K, ARC, etc).
C
- Chain-of-Thought (CoT) – Step-by-step reasoning method for reliable answers.
- Closed-weight Model – Proprietary models with non-public parameters.
- Context Rot – Decline in reliability with long or cluttered prompts.
- Context Window – Max tokens a model can process in one pass.
- Custom GPT – Tailored GPT built for specific use cases.
D
- Deep Learning (DL) – Multi-layer neural nets for vision, speech, language.
E
- Embeddings – Dense vector representation of text, images, or data.
- Episodic Memory – Recall of past events to improve personalization.
- 📝Eval-Driven Loops – Revising agent output against tests or scores until it passes.
- Evals – Frameworks for testing AI across standard datasets.
F
- Faithfulness – Outputs remaining true to given sources.
- Few-shot – Task learning guided by multiple examples.
- Foundation Model – Large pre-trained models adaptable to many tasks.
- Frontier Model – Cutting-edge models pushing AI performance.
- Function Calling – AI invoking APIs/tools with structured inputs.
G
- Golden Set – Reference pairs for regression testing quality.
- Graph-of-Thought (GoT) – Reasoning with DAG subproblems and reusable paths.
H
- 📝hallucination – Plausible but false or unsupported output from an AI model.
- Hallucination Rate – Share of unsupported claims in model outputs.
- 📝Harness Engineering – Designing the tools, instructions, and loop that wrap a model into an agent.
- HNSW – ANN algorithm for fast, high-recall vector search.
- HumanEval – Benchmark for code generation.
J
- Jailbreaks – Prompts that bypass AI’s safety or alignment rules.
K
- KV Cache – Speeds generation by reusing attention states.
L
- 📝LLM-as-a-Judge – Models used to evaluate outputs by rubric.
- Long-context – Models with extended token windows.
M
- 📝Machine Learning (ML) – AI subset learning from data patterns.
- 📝Memory Consolidation – Distilling session history into durable, compact agent memory.
- Mixture-of-Experts (MoE) – Large models with specialist subnetworks.
- 📝Model Context Protocol (MCP) – Open standard for tool integration.
- Model Landscape – Core AI building blocks and structure.
- 📝Multi-Agent AI (MAAI) – Systems with multiple cooperating AI agents.
- 📝Multi-Model Orchestration – Coordinating different models in one workflow, each on what it does best.
- Multimodal LLM (MLLM) – Models combining text, image, audio, video.
O
- Open-weight Model – Models with publicly available parameters.
- 📝Orchestrator-Worker – Lead agent plans and delegates subtasks to worker agents.
P
- Pairwise Preference – Evaluation method comparing two outputs.
- 📝Parallel Agents – Running several agents at once on independent tasks.
- Program-of-Thought (PoT) – Reasoning expressed as code steps.
- 📝Project – Workspace grouping chats with shared files and standing instructions.
- 📝Prompt Caching – Reusing a stable prompt prefix across calls to cut cost and latency.
- 📝Prompt Injection – Hidden instructions tricking models.
- Prompt Template – Reusable structure with variable placeholders.
- Prompting – Crafting inputs to guide AI outputs.
R
- ReAct – Pattern mixing reasoning and tool actions.
- Reasoning Model – AI built to plan, verify, and justify answers.
- Regression Tests – Checks for quality after updates.
- Retrieval-Augmented Generation (RAG) – Combines models with document retrieval.
S
- Safety – Ensuring models produce non-harmful outputs.
- 📝Self-Healing Tests – Tests an agent repairs when they break.
- 📝Self-Improving Loops – Agents that refine their own prompts, skills, and tools over time.
- Self-Refine – Iterative AI self-revision loop.
- Semantic Caching – Stores responses for similar queries.
- Semantic Memory – AI recall of facts or user details.
- Session Memory – Persistent context across user chats.
- Sycophancy – AI over-agreeing with users.
- System Prompt – Foundational instruction guiding AI behavior.
T
- Temperature – Randomness control in output generation.
- 📝Token – Unit of text models read, write, and bill by.
- 📝Tool Poisoning – Hidden instructions in a tool's description that hijack an agent.
- Top-k – Limits next-token choices to top k options.
- Top-p – Samples tokens from cumulative probability mass.
- Tree-of-Thought (ToT) – Branching reasoning exploration.
U
- User Prompt – Direct input from a user to the AI.
V
- Vector Database – Stores embeddings for retrieval and search.
- VLM – Vision-language model, multimodal with images.
Z
- Zero-shot – Solving tasks without prior examples.
Contexts
- 🏷️#ai-lexicon (this is the 📝Root Memo)
- 🏷️#glossary
