Episodi

  • Llm Inference Gpu Requirements 2024

    Llm Inference Gpu Requirements 2024
    Jul 14 2026
    Build Log / Signal Notes An anxious, rising tide of computational cost. The unspoken burden on every engineering team’s budget. This is a signal cut through the noise. A deep look at the quiet, 28% leap in GPU memory demands for LLMs—and why your infrastructure bill is feeling the strain. Host Nick Creighton details the precise techniques he’s used in production to cut those requirements in half, without sacrificing output quality. A quiet efficiency discovered in the code. Listen to the calibration. A companion blog post with benchmarks is available here. Find the signal.
    Mostra di più Mostra meno
    17 min
  • Fine-Tune Llama 3 For Document Summarization

    Fine-Tune Llama 3 For Document Summarization
    Jul 14 2026
    A forgotten file. A 47-page legal labyrinth. We’re all drowning in dense documents, spending hundreds of hours a year just trying to understand the fine print. But what if you had a second brain, fine-tuned to cut through the noise? Nick opens his build log on a new AI tool that processes a 50-page contract in 90 seconds, transforming a grueling task into a five-minute review. It’s a quiet revolution in document analysis. Dive into the details on our blog. Let’s get back to building.
    Mostra di più Mostra meno
    17 min
  • Local Rag With Ollama Tutorial

    Local Rag With Ollama Tutorial
    Jun 22 2026
    The hype around local AI often crashes into the reality of ten-gigabyte downloads and cooling fans spinning like jet engines. It’s a promise of privacy that feels violently out of reach. In this episode, we bypass the academic noise and hardware meltdowns. We are deploying an offline Retrieval-Augmented Generation system that breathes life into your documents without sending a single byte to the cloud. No API keys. No monthly invoices. Just a clean, efficient stack running on a standard laptop. It is the sound of productivity, reclaimed from the chaos of complex tutorials. Get the written walkthrough at [Link] Listen to build your local archive.
    Mostra di più Mostra meno
    13 min
  • Ai Agent Frameworks Eval 2024

    Ai Agent Frameworks Eval 2024
    Jun 22 2026
    The carnival rides are shutting down. The demos are over. Building AI agents in 2024 on nothing more than a loop and a prayer isn't just risky—it's a structural failure waiting to happen. We’ve seen the infinite loops. We’ve burned the API credits. We’ve watched hallucinations compound into total system collapse. This is the shift from hype to reliability. We strip away the magic to look at the frameworks that actually keep production systems running when things get weird. It’s time to stop hoping your prompt works and start building a house that stands. Read the companion blog post. Press play and let’s ship.
    Mostra di più Mostra meno
    15 min
  • Fine-Tune Llama 3 706B Model Locally

    Fine-Tune Llama 3 706B Model Locally
    Jun 15 2026
    The hum of a server. The click of a terminal. Forget the API; this is about running the colossal Llama 3 model yourself. A 706B parameter AI, in-house, offline. Host Nick Creighton maps the frontier of true data privacy, where your internal documents and codebases never leave your control. This is the blueprint for building a private AI data center, covering the hardware reality check and the parallel power of fine-tuning and RAG. Ready to ship it? Listen here. Read the companion post: [Link to blog post]
    Mostra di più Mostra meno
    17 min
  • Fine Tune Llama 3 For Sql Query Generation Tutorial

    Fine Tune Llama 3 For Sql Query Generation Tutorial
    Jun 15 2026
    You trust the AI to write your SQL. It's going to cost you. This week, we fine-tune Llama 3 in an afternoon for under fifty dollars, turning a brittle liability into a precise, private tool. It’s about the gap between a convincing answer and a correct one. The quiet panic when a hallucinated column sends your dashboard off a cliff. We’re moving past generic chatbots and into something that understands your schema, your logic, your stakes. Build the detail-oriented, credible alternative. Full walkthrough in the companion post. The next query it writes could save your morning. Listen.
    Mostra di più Mostra meno
    15 min
  • Llm Evaluation Metrics Explained 2024

    Llm Evaluation Metrics Explained 2024
    Jun 8 2026
    Build Log, with Nick Creighton. This week, the models went quiet. The outputs, once reliable, turned bland and hollow. When your systems falter and hope is your only strategy, it’s time to move past the demo. Nick recounts the death of the "vibe check"—that quick, gut-feeling review that fails when you’re not looking. He spent the last three months building a real validation pipeline, shifting from fragile prompts to a system that actually earns its keep. This is about fighting the silent decay of AI performance, about replacing theory with a foundation that holds while you sleep. For more detail on the validation build, find the companion post [link]. Listen to the full episode.
    Mostra di più Mostra meno
    9 min
  • Openai Api Vs Local Llama 3 Cost 2024

    Openai Api Vs Local Llama 3 Cost 2024
    Jun 8 2026
    Signal Notes. March 25th, 2024. A cold number on the dashboard at dawn. The hum of a server, the quiet click of a key. The cost of intelligence is plummeting, a 92% freefall in 14 months. The gap between cloud and local inference has narrowed to a sliver, a decimal point on a billing report. The raw data from Nick’s production run: $347.22 for the API, $412.00 for the rented hardware, plus the hidden tax of maintenance scripts and library conflicts. It’s a story told in tokens and receipts, not theory. A vibe of pragmatic calculation. The quiet awe of a shifting landscape. Read the numbers: [companion blog post link] Listen to the math.
    Mostra di più Mostra meno
    25 min