Skip to content
Technology Munch

Index

The index

Everything here, in six sections. Start with the mechanism if the vocabulary is new; start with privacy if you have already been pasting things into a chat box at work.

Almost every surprise these tools produce follows from the mechanism. Ten minutes here prevents a year of confusion about hallucination, forgetting, and why the same question gives two answers.

  1. What a Language Model Is Doing

    Not a database, not a search engine, not a reasoning machine in the way people assume. The mechanism explains almost every surprise these tools produce.

    Explainer

  2. Why Models Invent Things

    Fabrication is not a bug being fixed. It is the same process that produces correct answers, operating where the training data was thin.

    Explainer

  3. Context Windows and Memory

    The model has no memory between messages. What looks like conversation is the entire history being re-read every time, which explains several odd behaviours.

    Explainer

  4. Tokens, Cost and Length Limits

    Models process fragments rather than words or characters. This explains pricing, length limits, and why some languages cost several times more than others.

    Reference

  5. Training Cutoffs and Stale Answers

    Every model has a date after which it knows nothing, and it will answer questions about that period anyway, confidently and wrongly.

    Explainer

  6. Reasoning Modes: Cost and Benefit

    Models that work through steps before answering are genuinely better at some problems and no better at others. Knowing which is which saves time and money.

    Analysis

  7. Agents: What They Cannot Do

    An agent is a model given tools and permission to act in a loop. That is genuinely useful and it introduces failure modes a chat interface does not have.

    Analysis

  8. Open Weights vs Closed Models

    The distinction is about who controls the model file, and it determines your privacy position, your costs and your exposure to a vendor's decisions.

    Analysis

Rankings go stale in a quarter. What lasts is knowing how to test a product on your own work, what a free tier costs you, and which questions a vendor cannot dodge.

  1. Evaluating an AI Tool in 20 Minutes

    A repeatable test that separates products doing real work from interfaces passing your text to someone else's model with a markup.

    Procedure

  2. The Wrapper Problem

    Most AI products are an interface over someone else's model. Sometimes that interface is worth the money and often it is a prompt.

    Analysis

  3. Comparing Assistants Properly

    Rankings go stale within a quarter. The durable comparison is about interface, integration, data policy and how each one fails.

    Procedure

  4. What a Free AI Tier Costs You

    Free AI access is funded somehow. Knowing which model of funding you are inside determines what you should put into the box.

    Analysis

  5. Specialised Tools vs General Ones

    General assistants have absorbed most of what narrow AI products did. Four conditions still favour the specialist; the rest is cancellable.

    Analysis

  6. Running Models Locally

    Local models are private, free per use, and slower and weaker than hosted ones. The gap has narrowed enough that the calculation has genuinely changed.

    Analysis

  7. The AI You Already Pay For

    Before subscribing to anything new, check what your existing tools now include. A significant amount of it arrived without announcement and is unused.

    Reference

  8. Reading AI Benchmarks

    Benchmark scores are real measurements of narrow things. What they predict about your work, and the specific ways the numbers are made to look better.

    Reference

  9. Hardware for Local Models

    Memory is the constraint, not processing speed. What each tier of hardware actually runs, and why the obvious upgrade is frequently the wrong one.

    Reference

  10. Real AI Product or Demonstration?

    This field produces more impressive demonstrations than working products. The signals that distinguish them, and the questions vendors cannot dodge.

    Checklist

Where these tools genuinely help with writing, where they leave a recognisable shape, and the verification habits that stop a fabricated citation ending up under your name.

  1. First Drafts That Do Not Look It

    The tell is not vocabulary. It is structural sameness, hedging, and a particular kind of empty competence. What to do about each.

    Procedure

  2. Detectors and Humanisers

    One category accuses innocent people, the other makes text worse to evade it. The whole exchange rests on a task that cannot be done reliably.

    Analysis

  3. A Research Workflow That Holds Up

    The failure mode is a fluent summary of sources that do not say what it claims. A sequence that catches it before you publish.

    Procedure

  4. AI for Search Content, Honestly

    Generating volume is now trivial, which is exactly why it stopped working. What search engines actually penalise, and what remains worth doing.

    Analysis

  5. Editing Rather Than Generating

    The underused mode, and the one that improves your writing instead of replacing it. Specific prompts that produce useful criticism rather than praise.

    Procedure

  6. What Machine Translation Misses

    Good enough for understanding, risky for publishing, and dangerous in specific situations. Where the line falls and how to work across it.

    Analysis

  7. Transcription and Voice Tools

    Automatic transcription became genuinely good, with specific failure patterns that matter if anyone relies on the transcript.

    Reference

  8. Where AI Writing Help Works

    A candid list of tasks where using a model is straightforwardly good, and where it is a bad idea, without either enthusiasm or suspicion.

    Reference

Generated summaries feel efficient and reliably produce worse recall than notes you wrote badly yourself. What to automate, and what to keep doing by hand.

  1. AI Notes That Help You Learn

    Generated summaries feel efficient and reliably produce worse recall than notes you wrote badly yourself. What to automate instead.

    Analysis

  2. AI for Coursework: The Limits

    What these tools do well for a student, what they do badly, and where the line between help and academic misconduct actually sits.

    Analysis

  3. AI in Teaching: What Helps

    Most classroom AI products solve problems teachers do not have. The genuine wins are administrative, and the genuine risks are about assessment design.

    Analysis

  4. Reliable Analysis and Charts

    Arithmetic done in text is unreliable. Arithmetic done by executing code is not. Which mode your tool is in determines whether you can trust the number.

    Procedure

  5. Running a Useful One-to-One

    The default version is a status update the manager already had. What changes when the meeting belongs to the other person.

    Procedure

  6. Thinking When Answers Come Easily

    A fluent answer to any question in three seconds changes the failure mode. The habits that matter now are about interrogation rather than recall.

    Analysis

  7. What Meeting Summaries Get Wrong

    Automatic notes are convenient and confidently wrong in one specific way that causes real problems: who agreed to do what.

    Reference

  8. Spaced Repetition, With and Without AI

    The technique with the strongest evidence behind it in learning research. What AI changes about it, which is less than the marketing suggests.

    Procedure

Generation gets the attention; the editing automation does the work. Plus one note on night sky photography, which needs no AI at all.

  1. What Image Generation Is For

    Good at illustration and mood, unreliable at anything specific, and legally unsettled for commercial use. Where it fits and where it does not.

    Analysis

  2. AI Video Tools That Save Time

    Generation gets the attention and editing automation does the work. The unglamorous features are where hours actually disappear.

    Reference

  3. AI Photo Editing Worth Learning

    Object removal, masking and noise reduction quietly became excellent. What they do well, where they fail, and the honesty question for documentary work.

    Reference

  4. Photographing the Night Sky

    The Milky Way with a basic camera and a tripod, and the arithmetic that decides your exposure. No tracking mount required to start.

    Procedure

What these tools do with what you type, the security problem nobody has solved, and the short list of habits that covers most realistic risk — including the ones that changed because fraud got fluent.

  1. What AI Tools Do With Your Text

    Four things can happen to a prompt, and which ones apply depends on settings most people never open. The specific questions to ask of any tool.

    Reference

  2. Prompt Injection Matters to You

    A model cannot reliably tell your instructions from instructions hidden in a document it reads. Once tools can act, that becomes your problem.

    Explainer

  3. Free VPN Apps and Your Data

    A VPN sees everything you do, and running one costs money. The arithmetic of a free VPN only works one way, and researchers have shown how.

    Analysis

  4. Antivirus Now: What Still Matters

    The built-in protection on modern systems is genuinely good. What third-party products add, what they cost you, and where the actual risk moved.

    Analysis

  5. What a Network Security Key Is

    The phrase appears at the worst moment and means one of three different things. How to tell which, and the settings worth changing while you are in there.

    Explainer

  6. Deleting Search History Properly

    Clearing the browser does almost nothing. The record lives in your account, and the setting that stops it accumulating is a separate one.

    Procedure

  7. What Your IP Address Reveals

    It shows an approximate location and your provider. It is not your home address, and the sites claiming to find people by it are selling something.

    Explainer

  8. How AI Changed Scams

    The tells everyone was taught — bad grammar, obvious fakes — are gone. The defences that survive are about process rather than perception.

    Analysis

  9. Browser Extensions and Permissions

    An extension can read and change everything you do in the browser. The risk is not that they start malicious — it is that they change hands.

    Analysis

  10. Post-Quantum Encryption

    A real transition is underway for real reasons, on a timescale that matters now for some data and not at all for most people's daily use.

    Explainer

  11. Deception Technology: Decoys

    Planting credentials and files nobody legitimate should touch. Very high precision, narrow coverage, cheap enough that most should use some.

    Explainer

  12. Online Safety Advice That Holds

    Much of the standard advice is obsolete. What is left is short, unglamorous, and covers the large majority of realistic risk.

    Checklist

50 notes in total