Prompt Engineering

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.

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.

Retrieval-Augmented Generation (RAG) is a technique that enhances LLM responses by retrieving relevant documents from an external knowledge base before generating an answer. This allows the model to ground its output in up-to-date, domain-specific information rather than relying solely on its training data. RAG is widely used in enterprise chatbots, documentation assistants, and search-powered AI applications.

Multimodal AI refers to models that can process and generate multiple types of data — such as text, images, audio, and video — within a single system. Models like GPT-4o and Claude can accept both text and image inputs, enabling use cases like visual question answering, document analysis, and UI understanding. This convergence is blurring the lines between previously separate AI disciplines.

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.