Subscribe
Topic / page 9

Explainers

Articles, page 9

161-180
  1. How to Write AI Image Prompts: A Beginner's Guide

    A plain-English guide to AI image prompts: the parts of a good prompt, how to get text into an image, how to edit and iterate, how to use reference images, common mistakes, and copy-paste examples for photos, illustrations, logos, product shots and UI mockups.

    Image Generation
    9 min read
  2. What Are Tokens? How AI Models Count Text and How Usage Is Billed

    Tokens are the chunks of text AI models read and write. How tokenizers split words, why counts differ by model and language, how images and audio count too, and how pay-per-use billing works, with sources from Google, IBM, Hugging Face and Anthropic.

    LLM
    8 min read
  3. What Is a Context Window? How Much an AI Model Can Read at Once

    A context window is how much text an AI model can look at in one go, including its own reply. What fills it, what happens when it runs out, why bigger is not automatically better, and how to work within it, with sources from IBM, Anthropic, Google and the Lost in the Middle paper.

    LLM
    7 min read
  4. What Is an AI Agent? How AI Agents Work, Explained Simply

    An AI agent is an AI system that pursues a goal by choosing steps, using tools and checking results in a loop. How agents differ from chatbots and assistants, how the loop works, where agents help today, and the risks to watch, with sources from Anthropic, IBM, Google Cloud and OWASP.

    Agents
    8 min read
  5. What Is a TPU? Google's AI Chips Explained in Plain English

    A TPU is Google's custom chip for machine learning. Here is what it does, how it handles the matrix math inside AI models, how pods and slices work, how it compares with GPUs and CPUs, what the Edge TPU is, and who can use one, in plain English.

    Google
    9 min read