Sebastian Raschka

United States

Writer at Ahead of AI

Featured in: Favicon

medium.com Favicon

arxiv.org

substack.com (+1) Favicon

springer.com Favicon

kdnuggets.com Favicon

datasciencecentral.com Favicon

techmonitor.ai Favicon

turingpost.com Favicon

sebastianraschka.com Favicon

mdpi.com + 4 more

Articles

The State of Reinforcement Learning for LLM Reasoning

5 days ago | magazine.sebastianraschka.com | Sebastian Raschka

A lot has happened this month, especially with the releases of new flagship models like GPT-4.5 and Llama 4. But you might have noticed that reactions to these releases were relatively muted. Why? One reason could be that GPT-4.5 and Llama 4 remain conventional models, which means they were trained without explicit reinforcement learning for reasoning. Meanwhile, competitors such as xAI and Anthropic have added more reasoning capabilities and features into their models.
Top AI Newsletters of 2025

3 weeks ago | ai-supremacy.com | Ethan Mollick |Sebastian Raschka |Timothy Lee

This list is not exhaustive but features many of the top AI Newsletters on the internet today. 📚 Some of the factors used in the ranking are total paid subscriptions (this is the main criteria) engagement relative to list size⭐ highlighting emerging writers (also check out the “rising” leaderboards in tech in the app)💭 simply my own personal judgment (while browsing Substack’s Tech and Biz leaderboards & analyzing who is reading who that is a huge Venn diagram in and of itself).
The State of LLM Reasoning Models

1 month ago | magazine.sebastianraschka.com | Sebastian Raschka

Improving the reasoning abilities of large language models (LLMs) has become one of the hottest topics in 2025, and for good reason. Stronger reasoning skills allow LLMs to tackle more complex problems, making them more capable across a wide range of tasks users care about. In the last few weeks, researchers have shared a large number of new strategies to improve reasoning, including scaling inference-time compute, reinforcement learning, supervised fine-tuning, and distillation.
Understanding Reasoning LLMs

2 months ago | magazine.sebastianraschka.com | Sebastian Raschka

This article describes the four main approaches to building reasoning models, or how we can enhance LLMs with reasoning capabilities. I hope this provides valuable insights and helps you navigate the rapidly evolving literature and hype surrounding this topic. In 2024, the LLM field saw increasing specialization. Beyond pre-training and fine-tuning, we witnessed the rise of specialized applications, from RAGs to code assistants.
Understanding Reasoning LLMs

2 months ago | sebastianraschka.com | Sebastian Raschka

In this article, I will describe the four main approaches to building reasoning models, or how we can enhance LLMs with reasoning capabilities. I hope this provides valuable insights and helps you navigate the rapidly evolving literature and hype surrounding this topic. In 2024, the LLM field saw increasing specialization. Beyond pre-training and fine-tuning, we witnessed the rise of specialized applications, from RAGs to code assistants.
Understanding Multimodal LLMs

Nov 21, 2024 | substack.com | Sebastian Raschka

Sebastian is a machine learning and AI researcher with over a decade of experience in the field. He is very passionate about explaining complex technical concepts and "taking the magic out of AI."
Building A GPT-Style LLM Classifier From Scratch

Sep 21, 2024 | magazine.sebastianraschka.com | Sebastian Raschka

In this article, I want to show you how to transform pretrained large language models (LLMs) into strong text classifiers. But why focus on classification? First, finetuning a pretrained model for classification offers a gentle yet effective introduction to model finetuning. Second, many real-world and business challenges revolve around text classification: spam detection, sentiment analysis, customer feedback categorization, topic labeling, and more.
Building LLMs from the Ground Up: A 3-hour Coding Workshop

Aug 31, 2024 | magazine.sebastianraschka.com | Sebastian Raschka

If you’d like to spend a few hours this weekend to dive into Large Language Models (LLMs) and understand how they work, I've prepared a 3-hour coding workshop presentation on implementing, training, and using LLMs. Below, you'll find a table of contents to get an idea of what this video covers (the video itself has clickable chapter marks, allowing you to jump directly to topics of interest): 0:00 – Workshop overview 2:17 – Part 1: Intro to LLMs 9:14 – Workshop materials 10:48 – Part 2:...
New LLM Pre-training and Post-training Paradigms

Aug 17, 2024 | magazine.sebastianraschka.com | Sebastian Raschka

The development of large language models (LLMs) has come a long way, from the early GPT models to the sophisticated open-weight LLMs we have today. Initially, the LLM training process focused solely on pre-training, but it has since expanded to include both pre-training and post-training. Post-training typically encompasses supervised instruction fine-tuning and alignment, which was popularized by ChatGPT. Training methodologies have evolved since ChatGPT was first released.
Fine-Tuning GPT-2 for Spam Classification: A Live Coding Session with Sebastian Raschka

Jun 19, 2024 | hugobowne.github.io | Hugo Bowne-Anderson |Sebastian Raschka

Inference and ResultsAfter the first round of training, Sebastian evaluated the fine-tuned model on the test set. He initially achieved an accuracy of around 80%, which is a significant improvement over the random baseline of 50%. Then, after fixing another gotcha and rerunning the notebook,the model achieved an accuracy of 95% on the test set.