Stacey on Software: Machine-learning

Advocacy
  • Oppression in Machine Learning

    Popular media loves to talk about "artificial intelligence" these days. It is a hot topic, one riddled with misunderstanding. Artificial…

  • Is Machine Learning a Threat to You?

    All a Machine Learning model can do is regurgitate existing thoughts and ideas expressed in digital form in astonishing new ways according…

  • Diversion #1: Agents

    The idea of an Agent is something that has developed over the course of applying Large Language Models (LLMs) to problem solving. You can…

  • Diversion #2: LangChain & Pydantic

    I've been doing a lot of my ML coding in Python. Honestly, for a long time I resisted it, but the tooling moves so fast and is so simple to…

  • A Quick Update - Trying to Dig Myself Out

    It's been 4 months since the last post, and I wanted to put out this interstitial post just to cover the time lapse. Since my last post…

  • Systemic Oppression and Machine Learning

    Many words have been written about the biases in "AI" training datasets. I last blogged publicly on this topic about 6 years ago, and it…

  • Structured Semantics

    Back in June, I was playing with structured semantics as a way to interact with an LLM for applications. Today, I watched a video that made…

  • The Bionic Coach

    Introduction Being extraordinary, it's a good feeling. My first electronic enhancement was a calculator. Forget long arithmetic, this was…

  • What AI Tells Us About Ourselves

    I saw today that Bumble is incorporating into their business model a way for "AI" to "go on dates" instead of people. Selling their…

  • Leveraging Iteration and Decoupling

    You gotta love the "AI" newsfeed these days, fast and furious. So, along the path of writing this 6th instalment, a number of things emerged…

  • Agents are Hard

    Today, in "building LLM agents is hard". I'm experimenting with a novel problem-solving model using the little Qwen2.5 14B parameter model…

  • Complex Example

    Stepping Up the Complexity Up to this point in the blog series, we've laid a little groundwork, and demonstrated a very simplistic example…

  • It Will Do Whatever Fool Thing You Ask It

    A group of us sat down to do the Bowling Kata the other day, to see if we could get the GenAI to do the implementation as we wrote the spec…

  • What Do You Design?

    I was talking with a colleague today about how GenAI is rewriting all our playbooks. Not just the technical ones—the organizational ones too…

  • What Is a Developer?

    Thanks to a colleague, I came across this article today, and it's been energizing. The author and his editors at O'Reilly have put together…