YHacker Newsscreenshots

Screenshot of magazine.sebastianraschka.com: Sebastian Raschka's from-scratch video course on building reasoning models

First screen, captured 8 hours ago. Hover to scroll the page, or open the video.

Sebastian Raschka's from-scratch video course on building reasoning models

More from magazine.sebastianraschka.com →

Sebastian Raschka's Ahead of AI post presenting an eight-video, 11-hour course on coding LLM reasoning models from scratch in Python and PyTorch, accompanying his book.

What HN thinks

A fan club meeting for Raschka's books, briefly interrupted by one person asking who would ever want to learn things.

Raschka's teaching is excellent
Many commenters praise his LLM-from-scratch book and this course as readable, intuitive, and the place where things finally clicked, including for people who train models professionally.
Questioning practical value
A few argue from-scratch model guides are like building your own CPU, or mainly a personal-brand play, since real models need huge compute and data.
Learning for its own sake matters
Others reply that understanding how tech works by building small versions is worthwhile, and that open models can be further trained, so the skills do transfer.

Consensus: Most agree Raschka is a highly capable, long-established educator whose materials are among the best intros to how LLMs work.

Recommended in the comments

Build a Large Language Model (From Scratch) (book): Readers say it is very readable, top-down, and made concepts like autograd click.
CS231n (other): Mentioned as a comparable long-running, excellent teaching resource.

Summarised by Claude from the comment thread 6 hours ago.

Points: 528
Comments: 79
Best rank: #1
Posted: 2026-10-26 by sgiannopoulos
Category: Ai ml

reasoning-models llm pytorch reinforcement-learning inference-time-scaling distillation qwen3 video-course

All captures:

Full page

Full-page screenshot of magazine.sebastianraschka.com

Captured 8 hours ago. Click for the whole screenshot.

Looks similar

Screenshot of magazine.sebastianraschka.com: Understanding Reasoning LLMs

Understanding Reasoning LLMs (magazine.sebastianraschka.com)

442 points by sebg 1 year ago | 163 comments

Sebastian Raschka's Ahead of AI newsletter article explaining the four main approaches to building and refining reasoning LLMs.

reasoning-models llm inference-time-scaling reinforcement-learning

Screenshot of magazine.sebastianraschka.com: Controlling Reasoning Effort in LLMs

Controlling Reasoning Effort in LLMs (magazine.sebastianraschka.com)

58 points by ibobev 3 months ago | 3 comments

Screenshot of magazine.sebastianraschka.com: Building LLMs from the Ground Up: A 3-Hour Coding Workshop

Building LLMs from the Ground Up: A 3-Hour Coding Workshop (magazine.sebastianraschka.com)

910 points by mdp2021 2 years ago | 110 comments

Sebastian Raschka's Ahead of AI newsletter post presenting a 3-hour video coding workshop on implementing, training, and using LLMs from scratch.

llm large-language-models pytorch workshop

Screenshot of magazine.sebastianraschka.com: Components of a Coding Agent

Components of a Coding Agent (magazine.sebastianraschka.com)

266 points by MindGods 6 months ago | 81 comments

Screenshot of magazine.sebastianraschka.com: Finetuning Large Language Models

Finetuning Large Language Models (magazine.sebastianraschka.com)

201 points by headalgorithm 3 years ago | 63 comments

Screenshot of magazine.sebastianraschka.com: Understanding large language models: A cross-section of the relevant literature

Understanding large language models: A cross-section of the relevant literature (magazine.sebastianraschka.com)

255 points by headalgorithm 3 years ago | 25 comments

Related stories

Screenshot of magazine.sebastianraschka.com: Understanding Reasoning LLMs

Understanding Reasoning LLMs (magazine.sebastianraschka.com)

442 points by sebg 1 year ago | 163 comments

Sebastian Raschka's Ahead of AI newsletter article explaining the four main approaches to building and refining reasoning LLMs.

reasoning-models llm inference-time-scaling reinforcement-learning

Screenshot of magazine.sebastianraschka.com: Building LLMs from the Ground Up: A 3-Hour Coding Workshop

Building LLMs from the Ground Up: A 3-Hour Coding Workshop (magazine.sebastianraschka.com)

910 points by mdp2021 2 years ago | 110 comments

Sebastian Raschka's Ahead of AI newsletter post presenting a 3-hour video coding workshop on implementing, training, and using LLMs from scratch.

llm large-language-models pytorch workshop

Screenshot of scottaaronson.blog: The Mathocalypse

The Mathocalypse (scottaaronson.blog)

361 points by 6bitquant 19 days ago | 380 comments

Scott Aaronson blog post reacting to OpenAI releasing hundreds of AI-generated math results, including a claimed proof of Khot's Unique Games Conjecture.

ai-mathematics openai unique-games-conjecture complexity-theory

Screenshot of scottaaronson.blog: The Mathocalypse

The Mathocalypse (scottaaronson.blog)

15 points by philipfweiss 19 days ago | 1 comments

Scott Aaronson's Shtetl-Optimized blog post reacting to OpenAI releasing hundreds of AI-solved major math results, including one his wife worked on.

ai-mathematics openai scott-aaronson complexity-theory

Screenshot of github.com: Getting AI to work in complex codebases

Getting AI to work in complex codebases (github.com)

442 points by dhorthy 1 year ago | 368 comments

A GitHub markdown document from HumanLayer describing advanced context engineering techniques for getting AI coding agents to work in complex codebases.

context-engineering coding-agents llm ai-assisted-coding

Screenshot of ivanturkovic.com: AI Made Writing Code Easier. It Made Being an Engineer Harder

AI Made Writing Code Easier. It Made Being an Engineer Harder (ivanturkovic.com)

343 points by saikatsg 7 months ago | 242 comments

Blog post by Ivan Turkovic arguing that AI tools make producing code easier while making the broader job of being a software engineer harder.

ai-coding-assistants software-engineering developer-productivity llm