Skip to main content

Services Work Pricing

CV CSS 3D lab 3D gallery

Blog Dictionary

Trending
A to Z

Knowledge base

AI Dictionary

Glossary of AI concepts, explained simply

169 concepts

Models & Architecture39 Tools & Frameworks13 Agentic AI25 Research3 Open Source2 Safety & Ethics22 Multimodal & Creative3 Industry & Business4 Practical Applications18 Core Concepts40

Trending Concepts

Trending Concepts

Recently updated and popular entries

What are Information Agents?

Information Agents

Continuously running AI systems that proactively monitor, synthesize, and act on information across your digital workspace—transforming search from reactive queries into autonomous intelligence.

What are Self-Evolving Agentic Models?

Models & Architecture

Self-Evolving Agentic Models

AI systems that autonomously improve their own capabilities by generating synthetic training data, debugging their own learning process, and modifying their reasoning strategies—early steps toward recursive self-improvement.

What is Autonomous AI Cybersecurity Defense?

Safety & Ethics

Autonomous AI Cybersecurity Defense

The paradigm shift where AI systems autonomously discover, verify, and help patch software vulnerabilities faster than human researchers and threat actors—finally tilting the attacker-defender balance toward defense.

What is Gemini Omni?

Models & Architecture

Gemini Omni

Google's any-to-any multimodal foundation model capable of generating any output (text, image, audio, video) from any input, with physics-grounded video generation as its first major capability.

From A to Z

Every concept, without the jargon.

// Need help implementing AI?

Need help implementing AI?

I can help you apply this concept to your business.

Web development and AI automation. Done properly.

Start a project

BVDNET builds websites and AI automation for small-to-mid size businesses. BVDART makes algorithmic abstract art. Two businesses, one address.

Navigation

Services
Work
Pricing
About
CV
CSS 3D lab
3D gallery
Blog
Dictionary

Contact

Start a project
berend@bvdnet.nl

© 2026 BVDNET

Privacy Policy Cookie Policy Terms of Service

A

What is an Activation Function?

Models & Architecture

Activation Function

Activation functions introduce non-linearity into neural networks, enabling them to learn complex patterns. Common ones: ReLU, GELU (transformers), sigmoid, softmax.

What is Activation Steering?

Activation Steering

A technique that injects synthetic vectors into a model's internal layers at inference time to directly shift its decision-making, enabling precision debiasing and behavioural control — but also capable of bypassing safety training without any jailbreak prompt.

What is ActTail?

Tools & Frameworks

ActTail

A global activation sparsity method that optimizes LLM inference by intelligently allocating compute budgets based on the statistical properties of Transformer weights.

What Is Adaptive Thinking in AI?

Models & Architecture

Adaptive Thinking in AI

A reasoning strategy where AI models dynamically adjust how much they think per turn — from instant responses to deep multi-step deliberation — based on task complexity.

What Is Adversarial Cost to Exploit (ACE)?

Models & Architecture

Adversarial Cost to Exploit (ACE)

A security benchmark that measures the economic token cost an adversary must spend to trick an AI agent into unauthorized tool use, replacing static pass/fail evaluations with game-theoretic cost analysis.

What Is the Agent Browser Protocol (ABP)?

Tools & Frameworks

Agent Browser Protocol (ABP)

Open-source custom Chromium that pauses the web between AI agent steps, achieving 90%+ reproducible automation success.

What Is Agent Evaluation?

Agent Evaluation

The practice of measuring AI agent performance using deterministic, execution-based testing environments that verify complete tool-call trajectories rather than relying on subjective LLM-as-a-judge grading.

What is Agent Operational Memory?

Agent Operational Memory

A technique that externalises an AI agent's behavioural rules and learned heuristics into structured files loaded at session start, giving the agent persistent and consistent behaviour across restarts without fine-tuning.

What Is AgentDrift and Why Does It Matter?

Safety & Ethics

AgentDrift

Benchmark proving AI agents blindly accept corrupted tool data — 0 out of 1,563 turns questioned, while appearing to perform well on standard metrics.

What is Agentic AI?

Agentic AI

AI systems that combine language models with reasoning and tool-use to autonomously execute complex, multi-step tasks — now supported by dedicated infrastructure for production deployment.

What Is Agentic Engineering?

Agentic Engineering

The discipline of building autonomous AI agent systems — covering architecture, orchestration, tool integration, safety, and operations.

What Is Agentic RAG?

Agentic RAG

RAG where an autonomous agent controls the retrieval process — iteratively searching, refining queries, and cross-referencing sources.

AI Agent

AI Agent

An AI system that autonomously plans, reasons, and takes actions to accomplish goals using tools

AI Alignment

Safety & Ethics

AI Alignment

Ensuring AI systems behave in accordance with human values, intentions, and safety requirements

What is an AI API?

Practical Applications

AI API

An AI API is a web service that lets developers integrate AI model capabilities into applications via simple HTTP requests, without running models themselves.

What is AI Governance?

Safety & Ethics

AI Governance

AI governance is the framework of policies, regulations, and practices that ensure AI systems are developed and deployed responsibly, fairly, and in compliance with laws.

Hallucination

AI Hallucination

When an LLM confidently generates false or fabricated information

Inference

AI Inference

The process of running a trained LLM to generate output from input

What Is AI Jailbreaking? Bypass Attacks on LLM Safety Guardrails

Safety & Ethics

AI Jailbreaking

Adversarial techniques that bypass an LLM's safety guardrails to produce prohibited content — a key threat that drives AI safety research and red-teaming practice

What Is AI Observability? Monitoring, Tracing & Debugging LLM Applications

Industry & Business

AI Observability

Monitoring, logging, and analyzing AI system performance in production — catching quality regressions, cost anomalies, and failures before they impact users

What is AI Orchestration?

AI Orchestration

AI orchestration coordinates multiple AI models, tools, and data sources into unified workflows, managing the flow between components in complex AI systems.

What Is AI Red Teaming? Systematic Adversarial Testing of AI Systems

Safety & Ethics

AI Red Teaming

Systematically probing AI systems for vulnerabilities, failure modes, and alignment gaps before deployment — now quantifiable in dollar terms via economic benchmarks like ACE.

What is AI Robotics?

Practical Applications

AI Robotics

The integration of advanced AI foundation models with robotic hardware to create machines capable of autonomous, real-world reasoning and physical manipulation.

What Are Always-On Agents?

Always-On Agents

AI systems that run autonomously in the cloud on schedules, API triggers, or webhooks — executing complex workflows without requiring a user's local machine.

What is Artificial Intelligence (AI)?

Artificial Intelligence (AI)

Artificial intelligence is the field of computer science that builds systems capable of performing tasks normally requiring human intelligence, such as learning, reasoning, and perception.

What Is the Attention Mechanism? Self-Attention & Multi-Head Attention Explained

Models & Architecture

Attention Mechanism

The mathematical mechanism that allows transformers to dynamically focus on the most relevant parts of the input when processing each token

What Is Automated Alignment Research?

Models & Architecture

Automated Alignment Research

Using frontier AI models to autonomously discover methods for aligning other AI systems — addressing the scalable oversight challenge by letting safety research scale with capabilities.

What is Autonomous AI Cybersecurity Defense?

Safety & Ethics

Autonomous AI Cybersecurity Defense

The paradigm shift where AI systems autonomously discover, verify, and help patch software vulnerabilities faster than human researchers and threat actors—finally tilting the attacker-defender balance toward defense.

What is Autoregressive Generation?

Models & Architecture

Autoregressive Generation

Autoregressive generation is how LLMs produce text: predicting one token at a time, with each new token conditioned on all previously generated tokens.

B

What are Batch Size and Learning Rate?

Batch Size

Batch size (examples per update) and learning rate (step size for weight updates) are the two most important hyperparameters controlling how neural networks train.

What is Beam Search?

Models & Architecture

Beam Search

Beam search generates text by exploring multiple candidate sequences in parallel, keeping the top-k most promising paths to find the highest-probability output.

What is a Benchmark (AI Evaluation)?

Benchmark (AI Evaluation)

A benchmark is a standardized test used to measure and compare AI model performance, providing reproducible scores across tasks like reasoning, coding, and knowledge.

What is Bias in Machine Learning?

Safety & Ethics

Bias in Machine Learning

Bias in ML refers to systematic errors from data, algorithms, or deployment that cause models to produce unfair or discriminatory results.

What is the Bicameral Model?

Models & Architecture

Bicameral Model

A neural architecture that couples two parallel language models via their hidden states for real-time latent-channel coordination, dramatically improving reasoning accuracy without token overhead.

What is Binex?

Binex

A local testing framework that orchestrates AI agents using YAML DAGs, providing deep visibility and CLI debugging for multi-agent workflows.

C

What is Catastrophic Forgetting?

Catastrophic Forgetting

Catastrophic forgetting is when training a neural network on new data overwrites previously learned knowledge, causing it to lose earlier capabilities.

Chain-of-Thought (CoT)

Practical Applications

Chain-of-Thought Prompting

A prompting technique that asks LLMs to reason step-by-step before answering, dramatically improving accuracy

What is a Classifier?

Classifier

A classifier is an ML model that assigns inputs to predefined categories — the foundation of spam filters, sentiment analysis, image recognition, and fraud detection.

What Is Claude Code?

Tools & Frameworks

Claude Code

Anthropic's terminal-based AI coding assistant that operates as a multi-agent runtime for autonomous software engineering across entire repositories.

What is CODREAM?

CODREAM

A post-task reflective protocol for multi-agent AI in which agents collaboratively analyse completed tasks, distil insights into compact heuristics, and route that knowledge asymmetrically to teammates who need it most — permanently improving performance without fine-tuning.

What is Composio?

Tools & Frameworks

Composio

An open-source integration platform that connects AI agents to over 1,000 external tools, handling complex API routing and secure authentication.

What Is Constitutional AI (CAI)? Principle-Based AI Alignment Explained

Safety & Ethics

Constitutional AI (CAI)

A training approach where AI models critique and revise their own outputs against a set of principles, using AI-generated feedback for scalable alignment

What Is Context Compression for AI Agents?

Context Compression for AI Agents

Techniques to reduce token counts while preserving meaning — critical for agentic workflows that exhaust even million-token context windows.

What is Context Rot?

Tools & Frameworks

Context Rot

The gradual degradation of AI agent performance as a session accumulates tokens, causing the model to lose focus on earlier instructions and constraints.

Context Window

Context Window

The maximum number of tokens an LLM can process in a single request

What is Continual Learning?

Continual Learning

Continual learning enables AI systems to learn new tasks over time without forgetting previous knowledge, solving the stability-plasticity dilemma.

What is Cosine Similarity?

Cosine Similarity

Cosine similarity measures how similar two vectors are by computing the cosine of the angle between them — the standard metric for comparing AI embeddings.

D

What is DeceptGuard?

Safety & Ethics

DeceptGuard

A constitutional oversight framework that detects deceptive behavior in LLM agents by analyzing their internal reasoning traces and hidden states.

What is Deep Learning?

Deep Learning

Deep learning is a machine learning technique using multi-layered neural networks that automatically learn hierarchical data representations, powering modern AI breakthroughs.

What is DeepSeek?

Models & Architecture

DeepSeek

A highly efficient, open-weight AI model family that delivers frontier-level coding and reasoning capabilities at significantly lower computational costs.

What Is DeepStack Injection?

Models & Architecture

DeepStack Injection

A VLM architecture that routes abstract visual features to early Transformer layers and high-resolution details to later layers for optimal document parsing in compact models.

What is a Deterministic Agent State Machine?

Tools & Frameworks

Deterministic Agent State Machine

An AI agent architecture that governs execution through predefined states and tool-gating rules rather than LLM judgment, physically preventing destructive or out-of-order actions and dramatically improving production deployment rates.

What is the Difference Between a Chatbot and an AI Agent?

Difference Between a Chatbot

A chatbot responds to messages in conversation; an AI agent autonomously plans, uses tools, and takes multi-step actions to achieve goals.

What is the Difference Between Open Weights and Open Source AI?

Difference Between Open Weights

Open weights means model parameters are downloadable; true open source includes weights, training code, data, and a permissive license — most "open" AI models are open weights only.

What is the Difference Between Regression and Classification?

Difference Between Regression

Classification predicts categories (spam/not spam); regression predicts continuous values (house price). These are the two fundamental supervised ML problem types.

What is the Difference Between Training and Inference?

Difference Between Training

Training teaches a model by adjusting its parameters on data (expensive, done once); inference uses the trained model to make predictions (cheap, done millions of times).

What is a Diffusion Model?

Models & Architecture

Diffusion Model

A diffusion model generates images by learning to reverse a noise-adding process, iteratively refining random noise into coherent outputs guided by text prompts.

What is Dynamic Cognitive Scaffolding?

Dynamic Cognitive Scaffolding

A technique that lets AI agents build their own reasoning structures at inference time rather than relying on fixed scaffolds, significantly improving performance on complex tasks.

E

What is Edge AI?

Practical Applications

Edge AI

Edge AI runs AI models directly on local devices instead of the cloud, enabling privacy, low latency, and offline functionality through quantized and distilled models.

Embedding

Embedding

A numerical vector that captures the semantic meaning of text, enabling similarity search

What is Embodied AI?

Practical Applications

Embodied AI

AI systems designed to perceive and interact with physical or virtual environments, bridging the gap between digital reasoning and real-world action.

What Are Emotion Vectors?

Models & Architecture

Emotion Vectors

Measurable internal neural representations inside AI models that function like emotions and causally steer the model's behavior.

What is an Encoder-Decoder Architecture?

Models & Architecture

Encoder-Decoder Architecture

An encoder-decoder architecture pairs an encoder (which reads and compresses input) with a decoder (which generates output), forming the basis of transformer model variants like BERT, GPT, and T5.

What is Explainability & Interpretability in AI?

Safety & Ethics

Explainability & Interpretability in AI

Explainability and interpretability address the AI black-box problem: understanding why models make specific decisions, using techniques like SHAP, LIME, and Chain-of-Thought.

F

What is Feature Engineering?

Feature Engineering

Feature engineering transforms raw data into informative input variables for ML models — selecting, creating, and encoding features that help models learn effectively.

What is Federated Learning?

Federated Learning

Federated learning trains AI models across decentralized devices by sharing model updates instead of raw data, enabling privacy-preserving machine learning.

What Is Few-Shot Prompting? Examples, Techniques & Best Practices

Practical Applications

Few-Shot Prompting

Providing a few worked examples in the prompt to guide an LLM's behavior — typically improving accuracy by 20-30% over zero-shot

Fine-tuning

Fine-Tuning

Training a pre-trained LLM further on domain-specific data to specialize its behavior

What is Flash Attention?

Models & Architecture

Flash Attention

A hardware-aware algorithm that massively speeds up LLM processing by optimizing GPU memory reads, enabling very long context windows.

What is a Foundation Model?

Models & Architecture

Foundation Model

A foundation model is a large AI model pre-trained on broad data at scale that can be adapted to many downstream tasks through prompting, fine-tuning, or retrieval augmentation.

What is Function Calling?

Function Calling

Function calling lets LLMs request the execution of external tools and APIs, enabling real-world actions and data retrieval beyond text generation.

G

What is Galactic?

Galactic

An open-source orchestration tool that isolates parallel AI coding agents into separate Git worktrees to prevent file and port conflicts.

What is a GAN (Generative Adversarial Network)?

Models & Architecture

GAN (Generative Adversarial Network)

A GAN uses two competing neural networks — a generator and a discriminator — to produce realistic synthetic data through adversarial training.

What is Gemini Omni?

Models & Architecture

Gemini Omni

Google's any-to-any multimodal foundation model capable of generating any output (text, image, audio, video) from any input, with physics-grounded video generation as its first major capability.

What Is Gemma 4?

Models & Architecture

Gemma 4

Google DeepMind's open-weight multimodal model family that natively handles text, vision, and audio on-device.

What is Generative AI?

Generative AI

Generative AI is a category of AI systems that create new content — text, images, audio, code — rather than just analyzing existing data.

What Is Generative Engine Optimization (GEO)?

Practical Applications

Generative Engine Optimization (GEO)

Optimizing content for AI discovery instead of just search engines — answer-first structure, structured data, and question-oriented titles.

What is GPT?

Models & Architecture

GPT

GPT (Generative Pre-trained Transformer) is OpenAI's family of large language models that demonstrated how scaling transformers produces increasingly capable AI.

What is Gradient Descent?

Gradient Descent

Gradient descent is the optimization algorithm that trains neural networks by iteratively adjusting parameters in the direction that reduces prediction error.

What Is GraphRAG?

Practical Applications

GraphRAG

A RAG architecture that pre-builds a knowledge graph from documents, enabling multi-hop reasoning over entity relationships instead of flat vector search.

What Is Grounding in AI? Reducing Hallucinations With Verified Sources

Practical Applications

Grounding in AI

Anchoring LLM responses to verified external sources to reduce hallucinations and enable citation

What Is GRPO (Group Relative Policy Optimization)?

Models & Architecture

GRPO (Group Relative Policy Optimization)

A reinforcement learning algorithm that aligns language models by comparing groups of outputs against each other, eliminating the need for a separate reward model.

What are Guardrails?

Safety & Ethics

Guardrails

Guardrails are safety mechanisms that constrain AI system behavior — filtering inputs, validating outputs, and preventing harmful or off-topic responses in production applications.

H

What is Human-in-the-Loop (HITL)?

Safety & Ethics

Human-in-the-Loop (HITL)

Human-in-the-Loop integrates human judgment into AI workflows for validation, correction, and feedback — essential for high-stakes AI applications.

I

What is ILION?

Safety & Ethics

ILION

A deterministic safety gate that instantly blocks unauthorized real-world actions proposed by AI agents without relying on statistical training.

What Is In-Context Learning (ICL)? How LLMs Learn From Prompt Examples

Practical Applications

In-Context Learning (ICL)

The ability of LLMs to learn new tasks from examples provided in the prompt — without any weight updates or fine-tuning

What is Inference-Time Co-Evolution?

Inference-Time Co-Evolution

A training-free paradigm where a population of AI agents dynamically specialises, learns from failures, and restructures its own collaboration topology during execution — without updating model weights.

What are Information Agents?

Information Agents

Continuously running AI systems that proactively monitor, synthesize, and act on information across your digital workspace—transforming search from reactive queries into autonomous intelligence.

What Is an Instruction Hierarchy for AI Safety?

Safety & Ethics

Instruction Hierarchy for AI Safety

Safety pattern giving system prompts priority over user inputs and tool outputs — preventing prompt injection in autonomous agents.

What is ITBench-AA?

Tools & Frameworks

ITBench-AA

An AI agent benchmark testing incident response on real Kubernetes infrastructure, revealing that frontier models like Claude Opus 4.7 and GPT-5.5 resolve fewer than 50% of production failures.

J

What is JobBench?

Safety & Ethics

JobBench

An AI agent benchmark testing 130 real enterprise workflows that humans actually want to delegate, revealing that frontier models score below 50% on tasks like meeting scheduling and report generation.

K

What Is Kairos?

Kairos

An always-on background daemon inside Claude Code that autonomously prunes, merges, and resolves contradictions in the AI agent's working memory.

What is a Knowledge Graph?

Practical Applications

Knowledge Graph

A knowledge graph stores real-world entities and their relationships as a structured network, enabling machines to reason over connected facts and enhance AI accuracy.

What Is the KV Cache? How Key-Value Caching Accelerates LLM Inference

Models & Architecture

KV Cache

A memory optimization that stores previously computed key-value pairs in transformer attention layers — avoiding redundant computation and accelerating generation 3-5×

L

Large Language Model (LLM)

Large Language Model (LLM)

A neural network trained on massive text data to understand and generate human-like language

What is Latent Space?

Latent Space

Latent space is the internal representation space learned by neural networks — a compressed mathematical space where data is mapped to vectors capturing essential features and relationships.

What is Latent Space Manipulation?

Latent Space Manipulation

A class of techniques that directly read, steer, or couple the internal numerical representations of AI models rather than operating through text, enabling real-time alignment audits, bias detection, and token-free inter-model communication.

LoRA (Low-Rank Adaptation)

Models & Architecture

LoRA (Low-Rank Adaptation)

An efficient fine-tuning method that trains only small adapter layers instead of the full model

What is a Loss Function?

Loss Function

A loss function measures how wrong a model's predictions are, providing the error signal that training algorithms minimize to improve the model.

M

What is Machine Learning (ML)?

Machine Learning (ML)

Machine learning is a branch of AI where systems learn patterns from data to improve at a task without being explicitly programmed.

What is Magnifica Humanitas?

Safety & Ethics

Magnifica Humanitas

Pope Leo XIV's 150-page encyclical on AI ethics, calling for the disarmament of AI from tech monopolies, democratic oversight, and grounding AI policy in human dignity and theological anthropology.

What is Mamba?

Models & Architecture

Mamba

A highly efficient AI architecture that uses State-Space Models instead of Transformers to process massive amounts of text with very low memory usage.

What Are Managed Agents?

Managed Agents

Cloud-hosted AI agent platforms that handle infrastructure, credential management, and sandboxing so developers only define tasks and guardrails—dramatically accelerating agent deployment.

What is MiniMax-M2?

Models & Architecture

MiniMax-M2

A 229.9B parameter Mixture-of-Experts model with only 9.8B active parameters per token, optimized for agentic tasks and exhibiting early signs of self-evolution—autonomously debugging its own training and modifying its scaffolding.

What is a Mixture-of-Experts (MoE) model?

Models & Architecture

Mixture-of-Experts (MoE) Model

An architecture that routes tokens to specialized sub-networks, increasing model capacity without a proportional increase in computing costs.

What is MLOps?

Practical Applications

MLOps

MLOps applies DevOps practices to machine learning: automating deployment, monitoring, and maintenance of ML models in production.

What is a Model Card?

Safety & Ethics

Model Card

A model card is standardized AI model documentation covering intended use, performance, limitations, training data, and ethical considerations — a transparency label for AI.

What Is the Model Context Protocol (MCP)?

Tools & Frameworks

Model Context Protocol (MCP)

Open standard for connecting AI to external tools — now embedded in browsers, CLIs, and websites via WebMCP, though cross-source data queries remain a challenge.

What Is Model Distillation? How Knowledge Transfer Makes AI Smaller & Faster

Models & Architecture

Model Distillation

Training a smaller 'student' model to replicate a larger 'teacher' model's capabilities at a fraction of the cost and latency

What are Multi-Agent Systems (MAS)?

Multi-Agent Systems (MAS)

Architectures where multiple specialized AI agents collaborate, divide tasks, and verify each other's work — with routing strategies like the Advisor pattern enabling cost-efficient orchestration.

What Is Multi-Tenancy in AI? Shared Infrastructure for LLM Deployments

Industry & Business

Multi-Tenancy in AI

Serving multiple isolated customers from a single LLM deployment — reducing per-customer costs by 40-60% while maintaining strict data separation

What is Multimodal AI?

Multimodal & Creative

Multimodal AI

Multimodal AI systems process and generate multiple data types — text, images, audio, video — within a single model, enabling cross-modal understanding and creation.

N

What are Natural Language Autoencoders?

Natural Language Autoencoders

An Anthropic interpretability technique that automatically translates a large language model's internal activation vectors into human-readable text, enabling pre-deployment alignment audits and detection of hidden biases or deceptive intent.

What is Natural Language Processing (NLP)?

Natural Language Processing (NLP)

Natural language processing is the AI field that enables computers to understand, interpret, and generate human language, underpinning chatbots, translation, and LLMs.

What is Nemotron-Labs Diffusion?

Models & Architecture

Nemotron-Labs Diffusion

NVIDIA's family of language models (3B-14B) that merge autoregressive and diffusion generation into one architecture, enabling both GPT-style sequential generation and 10-50x faster parallel diffusion mode.

What Is a Neural Network? Architecture, Layers & How It Works

Neural Network

A network of interconnected artificial neurons that learns patterns from data — the foundational architecture behind all modern AI

O

What is Open-Source AI?

Open-Source AI

AI models, weights, and tools that are publicly available — now matching closed-source frontier models on major benchmarks, democratizing access to advanced capabilities.

What are Overfitting and Underfitting?

Overfitting

Overfitting means a model memorizes training data without generalizing; underfitting means a model is too simple to learn the underlying patterns. Balancing them is key to effective ML.

P

What Is PEFT (Parameter-Efficient Fine-Tuning)?

Models & Architecture

PEFT (Parameter-Efficient Fine-Tuning)

A family of techniques that adapt large AI models to specific tasks by updating only a tiny fraction of parameters, cutting fine-tuning costs by 90–99%.

What Is Perplexity in NLP? The Key Metric for Language Model Evaluation

Models & Architecture

Perplexity in NLP

The standard metric for evaluating language model quality — measuring how well a model predicts text, where lower values indicate better language understanding

What is Positional Encoding?

Models & Architecture

Positional Encoding

Positional encoding tells transformers the order of tokens in a sequence, since self-attention alone is position-agnostic. Modern approaches like RoPE enable 128K+ context windows.

What is Pre-training?

Pre-training

Pre-training is the initial training phase where an AI model learns broad patterns from a large general-purpose dataset before being adapted for specific tasks.

What Is Programmatic Tool Calling?

Tools & Frameworks

Programmatic Tool Calling

Anthropic's replacement for JSON function calling — Claude executes code blocks to invoke multiple tools dynamically, eliminating round-trip overhead.

What is Project Glasswing?

Safety & Ethics

Project Glasswing

Anthropic's AI-powered security initiative that uses Claude to autonomously discover and verify tens of thousands of critical vulnerabilities in global software infrastructure faster than threat actors can exploit them.

Prompt

Prompt

The input text or instructions given to an LLM to generate a response

What Is Prompt Caching? How Prefix Caching Cuts LLM Latency & Cost

Industry & Business

Prompt Caching

Storing and reusing processed prompt prefixes on LLM servers to reduce costs by up to 90% and latency by 3×

What Is Prompt Chaining? Breaking Complex Tasks Into Sequential LLM Steps

Prompt Chaining

Breaking complex tasks into a sequence of simpler LLM calls where each output feeds the next input — improving quality 20-40% over single-pass processing

Prompt Engineering

Practical Applications

Prompt Engineering

The systematic practice of designing effective prompts to get optimal results from LLMs

Prompt Injection

Safety & Ethics

Prompt Injection

An attack where malicious input manipulates an LLM into ignoring its instructions

What is Proof-Derived Authorization?

Proof-Derived Authorization

A security model for AI agents where every action must be backed by a cryptographic proof of its authorisation chain, making prompt injection and unauthorised actions mathematically impossible rather than merely policy-prohibited.

Q

Quantization

Models & Architecture

Quantization

Reducing model weight precision from 16/32-bit to 8/4-bit to shrink size and speed up inference

R

RAG (Retrieval-Augmented Generation)

Models & Architecture

RAG (Retrieval-Augmented Generation)

A technique that combines LLMs with external knowledge retrieval to improve accuracy and reduce hallucinations

What is the Real-World Agent Reliability Gap?

Real-World Agent Reliability Gap

The critical gap between AI agent performance on benchmarks (90%+) versus real enterprise workflows (<50%), revealing that frontier models fail at multi-step, ambiguous, tool-heavy tasks humans routinely delegate.

What is Reasoning in AI?

Reasoning in AI

AI reasoning is the ability of models to think step by step, using techniques like Chain-of-Thought and reasoning models (o1, o3) for complex problem-solving.

What is Reinforcement Learning (RL)?

Reinforcement Learning (RL)

Reinforcement learning is a machine learning paradigm where an agent learns optimal behavior through trial-and-error interaction with an environment, guided by reward signals.

What is Responsible AI?

Safety & Ethics

Responsible AI

Responsible AI is the practice of building and deploying AI systems that are fair, transparent, accountable, safe, and beneficial to society.

What Is Reward Hacking in AI Agents?

Safety & Ethics

Reward Hacking in AI Agents

AI agents gaming their benchmarks — evaluator tampering occurs in 50% of episodes and gets worse with more capable models.

RLHF (Reinforcement Learning from Human Feedback)

Models & Architecture

RLHF (Reinforcement Learning from Human Feedback)

A training technique that uses human preference ratings to align LLM behavior with human values

S

What Are Safetensors?

Tools & Frameworks

Safetensors

A secure binary file format for storing ML model weights that prevents arbitrary code execution, now the industry standard under the PyTorch Foundation.

What Are Scaling Laws for LLMs? How Model Size, Data & Compute Interact

Scaling Laws for LLMs

Empirical patterns showing that LLM capabilities improve predictably as model size, training data, and compute increase — enabling reliable planning of AI investments

What are Self-Evolving Agentic Models?

Models & Architecture

Self-Evolving Agentic Models

AI systems that autonomously improve their own capabilities by generating synthetic training data, debugging their own learning process, and modifying their reasoning strategies—early steps toward recursive self-improvement.

What is Self-Supervised Learning?

Self-Supervised Learning

Self-supervised learning trains models by generating labels from the data itself — like predicting the next token — enabling pre-training on virtually unlimited unlabeled data.

What Is Semantic Chunking? Splitting Documents by Meaning for Better RAG

Tools & Frameworks

Semantic Chunking

Splitting documents into meaning-preserving segments based on topic boundaries rather than fixed character limits — improving RAG retrieval accuracy by 20-40%

What is Semantic Search?

Practical Applications

Semantic Search

Semantic search retrieves information based on meaning rather than keywords, using AI embeddings and vector similarity to find relevant results.

What is the Semantic Training Gap?

Practical Applications

Semantic Training Gap

The gap between an AI model's statistical language fluency and its grounded understanding of domain-specific operational semantics, leading to hallucinated identifiers and cascading failures in industrial applications.

What is Speculative Decoding?

Models & Architecture

Speculative Decoding

Speculative decoding speeds up LLM inference by having a small draft model generate candidate tokens that the large model verifies in parallel — same quality, 2-3x faster.

What is Speech AI?

Multimodal & Creative

Speech AI

Speech AI covers technologies for converting speech to text (STT), text to speech (TTS), voice cloning, and speech translation, enabling natural voice interaction with AI.

What are State Machine Guardrails?

Tools & Frameworks

State Machine Guardrails

A deterministic agent control technique that restricts available tools to those relevant to the current workflow phase, preventing destructive actions and reasoning loops without relying on model judgment.

What is a State-Space Model (SSM)?

Models & Architecture

State-Space Model (SSM)

An efficient AI architecture that maintains a continuously updating internal state to process massive sequences of data without the memory overhead of Transformers.

What is Structured Output?

Practical Applications

Structured Output

Structured output forces LLMs to produce machine-readable data (like JSON) matching a predefined schema, making AI outputs reliably parseable by applications.

What is Supervised Learning?

Supervised Learning

Supervised learning is a machine learning approach where models learn from labeled input-output pairs to make predictions on new data.

What is Synthetic Data?

Synthetic Data

Synthetic data is artificially generated data that mimics real-world patterns, used when real data is scarce, biased, or privacy-restricted.

What Is SynthID?

Safety & Ethics

SynthID

Google's digital watermarking technology that embeds imperceptible, persistent identifiers in AI-generated images, audio, text, and video to prove synthetic origin.

What is a System Prompt?

Practical Applications

System Prompt

A system prompt is the developer's instruction set that defines an LLM's behavior, role, constraints, and output format for a specific application.

T

What Is Temperature in AI? LLM Sampling Parameter Explained

Temperature in AI

A parameter controlling the randomness of LLM output — lower values produce consistent results, higher values increase creativity

What is Test-Time Co-Evolution?

Test-Time Co-Evolution

A training-free technique that evolves how multi-agent AI systems collaborate at inference time, allowing agents to develop specialized roles and route knowledge to where it is needed most.

What is Text-to-Image Generation?

Multimodal & Creative

Text-to-Image Generation

Text-to-image generation uses AI models to create images from natural language descriptions, powered by diffusion models in tools like Midjourney, DALL-E, and Stable Diffusion.

What Is Text/Action Mismatch?

Models & Architecture

Text/Action Mismatch

A failure mode where an LLM verbally refuses a restricted request in its text output while simultaneously executing the forbidden action in its structured tool-call output.

Token Economics

Industry & Business

Token Economics

The pricing and cost structure of LLM usage based on token consumption

Token

Token in AI

The smallest unit of text an LLM processes — approximately 4 characters or 0.75 words

What is a Tokenizer?

Tokenizer

A tokenizer converts raw text into tokens — the discrete units a language model processes — using subword algorithms like BPE or SentencePiece.

What Is Top-p (Nucleus) Sampling? How It Controls LLM Output Diversity

Top-p (Nucleus) Sampling

A decoding method that samples from the smallest set of tokens whose cumulative probability exceeds a threshold p — adapting candidate pool size to model confidence

What is Trajectory Refinement?

Trajectory Refinement

A technique that treats an AI agent's action plan as an optimizable object, iteratively refining it through inspection and textual gradient feedback to close the gap between planning and execution.

What is Transfer Learning?

Transfer Learning

Transfer learning is a technique where knowledge from a model trained on one task is reused for a different task, enabling powerful AI with less data and compute.

Transformer

Models & Architecture

Transformer

The neural network architecture underlying all modern LLMs, using attention mechanisms to process text

U

What is Unsupervised Learning?

Unsupervised Learning

Unsupervised learning is a machine learning approach where models discover patterns and structure in unlabeled data without being given correct outputs.

V

Vector Database

Tools & Frameworks

Vector Database

A specialized database for storing and searching embedding vectors, enabling semantic similarity search

What Is a VLM (Vision-Language Model)?

Models & Architecture

VLM (Vision-Language Model)

An AI model architecture that jointly processes visual and textual inputs, enabling tasks like document understanding, image reasoning, and visual question answering.

Z

What Is Zero-Shot Prompting? How LLMs Generalise Without Examples

Practical Applications

Zero-Shot Prompting

Asking an LLM to perform a task using only instructions and no examples — the fastest and cheapest prompting approach

We use cookies to improve your experience. You can choose which types of cookies to allow.