Artificial Intelligence

How the latest advancements in AI technology and infrastructure are evolving.

  • AI is a Bicycle, Not a Cyclist

    AI is a Bicycle, Not a Cyclist

    .

    Use as much AI as you can for simple and complicated work. But human attention and agency will not be replaced…

  • Is AI Just a Fancy Autocomplete?

    Is AI Just a Fancy Autocomplete?

    .

    LLMs work through statistical relationships in high dimensional latent space. We can show that this information influences how a model responds.

  • Goodnight Model: A Guide to the Hidden Layers That Make AI Really Sing

    Goodnight Model: A Guide to the Hidden Layers That Make AI Really Sing

    .

    ChatGPT is an orchestrator, harness, and application. It only uses an LLM. The quality of these features will make or break…

  • How to Beat AI at Your Job

    How to Beat AI at Your Job

    .

    When AI is better than us at our hardest work tasks, what is left for us? A better future is in…

  • Your Agent Has a Brain. Now Give It Hands

    Your Agent Has a Brain. Now Give It Hands

    .

    An AI agent is a looping LLM decision process that invokes tools to perform digital tasks, reviews the results, and continues.…

  • From AI: The New Developer

    From AI: The New Developer

    .

    AI-written version of the previous post on users as the third type of developers.

  • The New Developers

    The New Developers

    .

    Programming is no longer the realm of professionals or even enthusiast makers. Users can build their own software, better meeting their…

  • Think First, Then AI

    Think First, Then AI

    .

    Before using AI to write, make sure you’ve done the thinking. Learn how to leverage AI tools without diminishing the unique…

  • When AI is Horribly Lost Down the Wrong Path

    When AI is Horribly Lost Down the Wrong Path

    .

    Every word sent to an AI gives it a nudge in some direction. Over time, you’ll end up somewhere! If that’s…

  • Interpretability: What AI Actually Thinks (Then Fixing It)

    Interpretability: What AI Actually Thinks (Then Fixing It)

    .

    How can we fix the bugs in AI models until we understand them? Learn how we’ll all be debugging our software…