Skip to main content Ahead of AI logo
Sebastian Raschka
Twitter/X icon LinkedIn Icon GitHub icon

    Home Ahead of AI Logo Blog Books Courses LLM Gallery LLMs From Scratch Reasoning Models Talks
    From Scratch Blog Archive Research About

    Reasoning Models From Scratch: Code Setup

    RSS Feed Ahead of AI Logo Subscribe via Email

    Aug 30, 2026
    by Sebastian Raschka

    A little video that

    • explains the relationship between conventional LLMs and reasoning models (and agents),
    • philosophizes about “from scratch” approaches,
    • and explains how to install the Python and PyTorch requirements with uv.

    The video is here: Build A Reasoning Model From Scratch #1: Motivation & Code Setup.

    YouTube thumbnail for a Build a Reasoning Model From Scratch video about motivation and code setup

    The first video in the Build a Reasoning Model From Scratch series.

    Source: website version of my Substack note.

    Read Next

    Pre-Training Without Learning Rate Decay A quick comparison of LLM pre-training recipes using cosine decay, warmup-stable-decay, or constant learning rates with checkpoint averaging. From Full to Hybrid Attention in LLMs How open-weight LLMs are shifting from full attention to hybrid and sparse designs, and what that means for long-context compute and memory. Open October LLM Architecture Roundup A roundup of ten open-weight LLM architecture releases from October 2026, covering attention mechanisms, hybrid layers, and MoE designs.
    RSS Ahead of AI Logo Subscribe via Email




    © 2013-2026 Sebastian Raschka