Every Solana term, protocol, and concept -- explained without the BS. Search, filter, and actually learn something.
A neural network trained on vast text corpora to understand and generate human language. LLMs (GPT-4, Claude, Llama, Gem...
The neural network architecture underlying modern LLMs, introduced in 'Attention Is All You Need' (2017). Transformers u...
A neural network component that allows models to weigh the relevance of different parts of the input when producing outp...
A large AI model trained on broad data that can be adapted for many downstream tasks. Foundation models (GPT-4, Claude,...
The practice of crafting input text (prompts) to guide LLM behavior and output quality. Techniques include: zero-shot (d...
The maximum amount of text (measured in tokens) an LLM can process in a single interaction. Larger windows enable proces...
The basic unit of text processed by language models—typically a word, subword, or character. Tokenizers (BPE, SentencePi...
The process of further training a pre-trained model on a specialized dataset to improve performance on specific tasks. F...
An AI architecture that combines LLMs with external knowledge retrieval. Instead of relying solely on training data, RAG...
A dense vector representation of text (or other data) in a continuous high-dimensional space where semantically similar...
A database optimized for storing and querying high-dimensional vector embeddings using similarity search (cosine distanc...
An autonomous AI system that can plan, use tools, and take actions to accomplish goals. Agents use LLMs as the reasoning...
An LLM capability where the model generates structured calls to external tools/functions rather than just text. The mode...
When an AI model generates plausible-sounding but factually incorrect information. LLMs hallucinate because they predict...
The process of running a trained model on new inputs to generate predictions or outputs. Inference is the 'using' phase...
The process of optimizing a model's parameters by exposing it to data and adjusting weights to minimize a loss function....
A training technique that aligns LLM outputs with human preferences. Process: (1) train a reward model from human compar...
AI models with publicly released weights that can be downloaded, modified, and self-hosted. Notable open models: Llama 3...
AI models that can process and generate multiple data types: text, images, audio, video, and code. Modern multimodal mod...
An AI tool that helps developers write, debug, review, and explain code. Examples: GitHub Copilot (inline suggestions),...
Blockchain protocols that coordinate and incentivize physical infrastructure through token rewards. DePIN projects on So...
Blockchain-coordinated networks that aggregate GPU resources for AI training and inference. Projects like Render Network...
The convergence of AI and blockchain technologies. Key patterns: AI agents executing on-chain transactions autonomously,...
Running AI/ML inference directly within blockchain smart contracts or verified through on-chain proofs. Current limitati...
The economic design of a cryptocurrency token: supply schedule, distribution, utility, incentive mechanisms, and value a...
A class of LLMs trained with reinforcement learning to generate step-by-step internal chain-of-thought before producing...
A prompting technique or model-native capability where the LLM produces intermediate reasoning steps before arriving at...
A persistent, developer-controlled instruction set provided to an LLM that defines its role, behavior, tone, constraints...
An LLM capability that constrains model output to conform to a predefined schema, typically JSON or XML, enabling reliab...
Anthropic's terminal-based agentic coding tool launched in early 2025 alongside Claude 3.7 Sonnet. It accepts natural-la...
An AI-native code editor (VS Code fork) with integrated LLM capabilities including multi-file editing, Composer mode for...
An AI-powered code editor (VS Code fork) originally created by Codeium and later acquired by Cognition. Launched in Nove...
An open standard introduced by Anthropic in November 2024 for connecting AI applications to external data sources, tools...
LangChain is a popular open-source framework for building LLM-powered applications, providing abstractions for chains, t...
An open-source multi-agent orchestration framework that uses a role-based paradigm where developers define AI 'crews' of...
The core iterative execution cycle of an agentic AI system: Perceive, Reason, Act, Observe, Repeat. At each iteration, t...
Showing 36 of 1001 terms