SebastianRaschka.com is the personal blog of Sebastian Raschka, PhD, an LLM research engineer whose work bridges academia and industry in AI and machine learning. On his blog and notes section he publishes deep, well-documented articles on topics such as LLMs (large language models), reasoning models, machine learning in Python, neural networks, data science workflows, and deep learning architecture. Recent posts explore advanced themes like “reasoning LLMs”, comparisons of modern open-weight transformer architectures, and guides for building, training, or analyzing neural networks and model internals.
142 articles from this blog
Analysis of 'pacing' in AI development: it means adding safety checks and release frameworks, not slowing down model training.
GPT-6 Astra, Looped Transformers, and Hidden ReasoningA Look at Recurrent Depth, Hidden Chains of Thought, and Recent Research on Looping Transformer
A lot of hype around OpenAI’s Astra model being a “recurrent depth or looped transformer”. Let’s debunk this a bit. About 2 months ago, I shared the a
Explains reasoning models vs LLMs, philosophizes about building from scratch, and shows Python/PyTorch setup with uv.
Author of 'Build a Reasoning Model (From Scratch)' announces two free live Q&A sessions on September 3 with AI book clubs, covering the book and its connection to LLM building.
Analysis of GLM-5.3-Flash architecture, a new LLM with hybrid attention and sparse MoE, compared to previous versions.
A detailed video walkthrough explaining how Claude watermarks AI-generated text, covering token sampling, detection, and removal.
Build an AI text detector from scratch, including dataset creation, model training, local deployment, and RLVR, with a UI for scoring text.
An explanation of Claude's text watermarking technique, its EU regulatory basis, and potential removal methods.
Announcement of 'Build a Reasoning Model From Scratch' book now on Amazon, with warnings about counterfeit copies in India and request for reviews.
Analysis of Meta's new open-weight Muse Glimmer 30B LLM, focusing on its architecture, KV-cache efficiency, and comparison to similar models.
The LLMs-from-scratch GitHub repo hits 100k stars; author shares highlights and future plans for new architectures and projects.
Analysis of Kimi K3's open-weight architecture, focusing on LatentMoE, attention residuals, and NoPE innovations for inference efficiency.
Overview of recent notable open-weight AI models including Nanbeige, Laguna, Motif, Solar, and Antares with architectural details.
Thanks everyone for all the kind words and feedback. Super happy that you are enjoying Build a Reasoning Model (From Scratch)! Unfortunately, there’s
Explains how LLMs learn low, medium, and high-effort reasoning modes, covering training and inference techniques for controlling reasoning effort.
Analysis of Thinking Machines Lab's new open-weight 975B MoE LLM, Inkling, with benchmark comparisons and architectural surprises.
Analysis of GPT 5.6's 72 configurations, mapping model choices and reasoning effort to performance and cost.
Announcement of the release of 'Build a Reasoning Model (From Scratch)', a book on implementing modern reasoning techniques for AI.
Tutorial on setting up a local coding agent using open-weight LLMs and open-source tools as an alternative to Claude Code and Codex.
