What are you curious about?
48 results
Agentic AI
Explain what "agentic" means beyond a single agent definition
Agents
Explain what an AI agent is and how its loop works
Attention mechanism
Explain what attention lets tokens do
Context compaction
Explain why long-running AI interactions need context compaction
Context engineering
Explain what context engineering is
Cosine similarity
Explain cosine similarity as a comparison of vector direction
Embeddings and vector representations
Explain how embeddings turn text and other data into vectors
Encoder-decoder models
Explain the role of encoders and decoders
Fine-tuning a pre-trained model
Explain what fine-tuning changes in a model
Harness Engineering
Explain what a harness is in an agentic AI system
Human-in-the-loop AI systems
Explain what human-in-the-loop means in an AI workflow
Hybrid search
Explain why keyword search and vector search each miss results the other finds
Inference — how models generate output
Describe what happens when a trained model receives a prompt
kNN and ANN nearest neighbor search
Explain how exact k-nearest neighbors (kNN) search works and why it gets slow on large collections
LLM architecture and attention
Explain the role of the transformer architecture in modern LLMs
Loop Engineering
Explain what the agent loop is and why it needs careful design
Model Context Protocol (MCP)
Explain MCP roles, transports, and the client-server lifecycle
Multimodal AI
Explain what multimodal AI means
Open-weight AI models
Explain what it means for an AI model to have open weights
Parameters and weights in AI models
Explain what parameters and weights represent in a trained model
Post-training AI models
Explain why a base model needs post-training
Pre-training AI models
Explain what pre-training teaches an AI model
Prompt caching
Explain how prompt caching reuses work for repeated input prefixes
Prompt engineering
Explain what prompt engineering is and why it matters
Quantization
Explain how quantization stores and computes model values with fewer bits
ReAct (Reason + Act)
Explain the ReAct pattern and the problem it solves
Recurrent neural networks (RNNs)
Explain how an RNN processes a sequence over time
Reinforcement learning from human feedback (RLHF)
Explain the main stages of classic RLHF
Semantic cache
Explain how a semantic cache answers similar prompts by comparing embeddings instead of exact text
Skills
Explain what skills are and how the SKILL.md format packages them
Speculative decoding
Explain how a draft model and target model cooperate during speculative decoding
Subagents
Explain how a parent agent delegates bounded work to subagents
System prompts
Explain what a system prompt does in a model request
What is a tokenizer?
Explain what a tokenizer is and where it sits in the model pipeline
Tokens in large language models
Explain what a token is and how it differs from words or characters
Tool Calling
Explain how structured tool calls and tool results move through an application
Transformers and BERT
Explain what a transformer is
Vector distance and similarity metrics
Explain what cosine, Euclidean, Manhattan, and dot product comparisons measure
Vector representations for AI systems
Explain how vectors represent meaning in AI applications
What is a large language model?
Explain what a large language model is and how next-token prediction produces full answers
Explore cosine similarity
Select word vectors, inspect the calculation, and see why direction matters more than length.
Explore embeddings
Build intuition for what embeddings actually do by playing with a small vector space you can see and measure.
Semantic search in a support inbox
Compare a typed customer query against ten saved support tickets and watch the nearest semantic match rise to the top.
Explore vector search
Watch a query become a vector, compare it with stored documents, and see how the nearest results are selected.
What Are Autoregressive Models? How GPT and Claude Generate Text
Understand autoregressive generation, compare masked and diffusion models, and separate what is known about GPT and Claude from undisclosed architecture details.
Why GPUs Became the Engine of Modern AI
How graphics hardware, matrix multiplication, CUDA, and Transformers came together to make GPUs essential for modern AI.
Why Does AI Writing Use So Many Em Dashes?
How edited training data, preference tuning, and the default assistant voice made em dashes common in AI-generated writing.
From Prototype to Production: A Reliability Checklist for LLM Applications
A practical checklist for turning an LLM demo into a reliable production feature with measurable behavior, safe boundaries, and useful observability.
No results found.
Try fewer words, a different term, or another content type.