Prompt Engineering

Tree shaking is a dead code elimination technique used by modern bundlers like Webpack, Rollup, and esbuild to remove unused exports from the final JavaScript bundle. It relies on the static structure of ES module `import`/`export` syntax to determine which code is actually referenced and safely discard the rest. For tree shaking to work effectively, libraries must use ESM format and avoid side effects in their module initialization, which is why the `sideEffects` field in `package.json` matters.

The transformer is a neural network architecture introduced in the 2017 paper "Attention Is All You Need" that revolutionized natural language processing. Unlike recurrent networks, transformers process entire sequences in parallel using a self-attention mechanism, which allows them to capture long-range dependencies efficiently. Virtually all modern LLMs, including GPT and Claude, are built on the transformer architecture.

A vector database is a specialized database optimized for storing, indexing, and querying high-dimensional vector embeddings. They enable fast similarity search, which is critical for RAG systems, recommendation engines, and semantic search applications. Popular vector databases include Pinecone, Weaviate, Qdrant, and pgvector for PostgreSQL.

Chain of Thought (CoT) is a prompting technique that encourages an LLM to break down complex reasoning into intermediate steps before arriving at a final answer. By explicitly reasoning through each step, models achieve significantly better accuracy on math, logic, and multi-step problems. Extended thinking and "thinking" tokens in models like Claude represent a built-in form of chain-of-thought reasoning.

Idempotency means that performing the same operation multiple times produces the same result as performing it once. This property is critical in automation and distributed systems where network failures or retries may cause a request to be sent more than once. APIs, payment processing, and deployment scripts should be designed to be idempotent so that retries are safe and don't create duplicate side effects.

Computer vision is a field of AI that trains machines to interpret and understand visual information from images and videos. Applications include object detection, facial recognition, autonomous driving, and medical image analysis. Modern computer vision leverages deep learning models like CNNs and vision transformers (ViT), and increasingly integrates with language models in multimodal AI systems.