Analytically Inclined

Tag: LLM

  • Stop Asking the LLM to Do the ML’s Job

    Stop Asking the LLM to Do the ML’s Job

    ·

    by

    scott
    in ,

    Before 2023, if you wanted a model to predict something, you had to build one. Gather data, pick features, choose an algorithm, train it, validate it, deploy it. That’s real work, and it’s work most business teams couldn’t do without a data scientist. Then LLMs showed up and could apparently do “AI stuff” without any…

  • LLM Context Windows: What Actually Matters

    LLM Context Windows: What Actually Matters

    ·

    by

    scott
    in

    The Context Window Arms Race Recently the LLM world has turned into a context window arms race. Google announces 2 million tokens. Anthropic pushes to 200K. OpenAI ups the ante. And everyone’s acting like bigger is automatically better. Here’s the thing though; most of us don’t actually need a 2 million token context window. And…