Skip to content
SparkTime, home
Topic · 72 pieces · page 4 of 4

AI

Using and building with AI.

Earlier in AI

Page 4 of 4

Learning

9 min read

Learning with AI Without Cheating Yourself

Using AI in your studies raises three separate questions: what your institution allows, whether you are actually learning, and whether you can still do the work without it. This article gives you honest rules, warning signs of dependency and a personal AI-use agreement you can write in ten minutes.

Learning

11 min read

How to Use AI to Learn a Difficult Technical Subject

'Explain everything about this topic' produces a wall of text you will forget. This article shows a better loop: tell the AI what you already know, learn in layers, try problems yourself, ask for hints instead of answers, and test your understanding. With a full worked session.

Technology

11 min read

Iterate, Break Tasks Apart and Reuse What Works

The first AI answer is a draft. This article teaches how to give feedback that actually improves it, how to ask the AI to critique and offer alternatives without being fooled by agreement, how to split big tasks into checkable steps, and when the real problem is not the prompt at all.

Technology

11 min read

Examples, Output Formats and Structured Output

Showing the AI one or two examples often beats three paragraphs of description. This article covers example-based prompting, choosing an output format, and requesting structured output such as JSON that a program or spreadsheet can use, with the checks that make it safe.

Technology

9 min read

Give AI the Right Context: Source Material and Long Documents

The single biggest upgrade to AI answers is not a cleverer prompt. It is giving the model the right material to work from and making it show where each claim came from. This article teaches grounding, quote-first answers and how to handle long documents.

Technology

11 min read

Why AI Sounds Right and Still Gets Things Wrong

Hallucinations are not random glitches. They follow predictable patterns that you can learn to spot. This article explains why fluent AI answers can be false, where errors cluster, and which habits reduce them, with an honest account of what no habit can fix.

Technology

12 min read

How Language Models Work: Training, Inference, Tokens and Context

You do not need maths to use AI well, but you do need a correct picture of what happens when you press enter. This article explains next-token prediction, training versus inference, tokens and the context window, and the practical habits each idea implies.

Technology

10 min read

AI, Machine Learning, Generative AI and LLMs: The Map

AI, machine learning, deep learning, generative AI, LLM, chatbot, model, agent: the words get used as if they mean the same thing. They do not. This article draws one simple map so every later article makes sense.

Technology

12 min read

Start Here: What You Can Do with AI and the Work Loop

A free, 35-article course on using modern AI well: what it is, how to ask, how to check it, and how to build habits that survive the next product update. This first article explains what to expect and introduces the six-step Work Loop you will use throughout.

CourseTechnology

7 min read

AI From Zero to Productive: A Practical Guide to Using AI Well

A free, 35-article course on understanding and using modern AI for learning, work, coding and career growth. It teaches transferable skills, not product tours: how language models behave, how to ask and give context, how to verify answers, how to protect privacy, when to automate, and how to build your own personal AI system.

Technology

5 min read

Writing Better AI Prompts: A Practical Guide

Most disappointing AI answers come from vague questions. Learn a simple structure for prompts, how to give context and examples, how to iterate, and how to check what comes back.

Technology

5 min read

How to Use AI for Studying Without Cheating Yourself

AI can be a patient tutor, a quiz master and a writing coach, or a shortcut that leaves you knowing nothing. Here is how to use it to learn faster, with prompts, routines and rules that keep you honest.

Technology

5 min read

How Do AI Chatbots Like ChatGPT and Claude Actually Work?

AI chatbots feel like magic, but the basic idea is simple: they predict the next piece of text, based on patterns learned from huge amounts of writing. Here is how that works and why they sometimes get things wrong.