RSS.Social

Sebastian Raschka, PhD

follow: @[email protected]

Posts

Kimi K3 Architecture Notes

A Few Notable Open-Weight Models This Week

Correction for Listing 6.5 in Build a Reasoning Model From Scratch

Controlling Reasoning Effort in LLMs

Inkling: A New Open-Weight 975B MoE with a Few Surprises

200,000 Subscribers

GPT 5.6 Has 72 Possible Configurations. What's A Good Default?

Build a Reasoning Model From Scratch Is Out

Using Local Coding Agents

Using Local Coding Agents

Local Open-Weight LLMs in Coding Harnesses

GLM-5.2 and IndexShare for Long-Context Sparse Attention

VibeThinker-3B and the Strength of Post-Training

North Mini Code and Agentic Coding Benchmarks

LLM Research Papers: The 2026 List (January to May)

Nemotron 3 Ultra and Latent MoE Scaling

MiniMax M2 and Production-Oriented Model Design

DeepSeek Sparse Attention From Scratch

Recent Developments in LLM Architectures: KV Sharing, mHC, and Compressed Attention

Recent Developments in LLM Architectures: KV Sharing, mHC, and Compressed Attention

Implementing LLM Architectures From Scratch

My Workflow for Understanding LLM Architectures

Components of A Coding Agent

Gemma 4 Architecture and Benchmark Notes

Claude Code's Real Secret Sauce Isn't the Model

LLM Architecture Gallery Diff Tool

A Visual Guide to Attention Variants in Modern LLMs

A Visual Guide to Attention Variants in Modern LLMs

New LLM Architecture Gallery

Nemotron 3 Super Throughput Notes

A Dream of Spring for Open-Weight LLMs: 10 Architectures from Jan-Feb 2026

State of AI 2026 with Sebastian Raschka, Nathan Lambert, and Lex Fridman

Categories of Inference-Time Scaling for Improved LLM Reasoning

The State Of LLMs 2025: Progress, Problems, and Predictions

The State Of LLMs 2025: Progress, Problems, and Predictions

LLM Research Papers: The 2025 List (July to December)

From Random Forests to RLVR: A Short History of ML/AI Hello Worlds

A Technical Tour of the DeepSeek Models from V3 to V3.2

Recommendations for Getting the Most Out of a Technical Book

Beyond Standard LLMs

DGX Spark and Mac Mini for Local PyTorch Development

Understanding the 4 Main Approaches to LLM Evaluation (From Scratch)

Understanding and Implementing Qwen3 From Scratch

From GPT-2 to gpt-oss: Analyzing the Architectural Advances

The Big LLM Architecture Comparison

LLM Research Papers: The 2025 List (January to June)

Understanding and Coding the KV Cache in LLMs from Scratch

Coding LLMs from the Ground Up: A Complete Course

The State of Reinforcement Learning for LLM Reasoning

First Look at Reasoning From Scratch: Chapter 1

Inference-Time Compute Scaling Methods to Improve Reasoning Models

Understanding Reasoning LLMs

Noteworthy LLM Research Papers of 2024

Implementing A Byte Pair Encoding (BPE) Tokenizer From Scratch

LLM Research Papers: The 2024 List

Understanding Multimodal LLMs

Building A GPT-Style LLM Classifier From Scratch

Building LLMs from the Ground Up: A 3-hour Coding Workshop

New LLM Pre-training and Post-training Paradigms

Instruction Pretraining LLMs

Developing an LLM: Building, Training, Finetuning

LLM Research Insights: Instruction Masking and New LoRA Finetuning Experiments?

How Good Are the Latest Open LLMs? And Is DPO Better Than PPO?

Using and Finetuning Pretrained Transformers

Tips for LLM Pretraining and Evaluating Reward Models

Research Papers in February 2024

Improving LoRA: Implementing Weight-Decomposed Low-Rank Adaptation (DoRA) from Scratch

Optimizing LLMs From a Dataset Perspective

The NeurIPS 2023 LLM Efficiency Challenge Starter Guide

Optimizing Memory Usage for Training LLMs and Vision Transformers in PyTorch

Finetuning Falcon LLMs More Efficiently With LoRA and Adapters

Accelerating Large Language Models with Mixed-Precision Techniques

Parameter-Efficient LLM Finetuning With Low-Rank Adaptation (LoRA)

Understanding Parameter-Efficient Finetuning of Large Language Models: From Prefix Tuning to LLaMA-Adapters

Finetuning Large Language Models On A Single GPU Using Gradient Accumulation

Keeping Up With AI Research And News

Some Techniques To Make Your PyTorch Models Train (Much) Faster

Understanding and Coding the Self-Attention Mechanism of Large Language Models From Scratch

Understanding and Coding Self-Attention, Multi-Head Attention, Causal Attention, and Cross-Attention in LLMs

Understanding Large Language Models -- A Transformative Reading List

What Are the Different Approaches for Detecting Content Generated by LLMs Such As ChatGPT? And How Do They Work and Differ?

Comparing Different Automatic Image Augmentation Methods in PyTorch

Curated Resources and Trustworthy Experts: The Key Ingredients for Finding Accurate Answers to Technical Questions in the Future

Training an XGBoost Classifier Using Cloud GPUs Without Worrying About Infrastructure

Open Source Highlights 2022 for Machine Learning & AI

Influential Machine Learning Papers Of 2022

Ahead Of AI, And What's Next?

A Short Chronology Of Deep Learning For Tabular Data

No, We Don't Have to Choose Batch Sizes As Powers Of 2

Sharing Deep Learning Research Models with Lightning Part 2: Leveraging the Cloud

Sharing Deep Learning Research Models with Lightning Part 1: Building A Super Resolution App

Taking Datasets, DataLoaders, and PyTorch’s New DataPipes for a Spin

Running PyTorch on the M1 GPU

Creating Confidence Intervals for Machine Learning Classifiers

Losses Learned

TorchMetrics

Machine Learning with PyTorch and Scikit-Learn

Introduction to Machine Learning

Introduction to Deep Learning

Datasets for Machine Learning and Deep Learning

Book Review: Deep Learning With PyTorch

How I Keep My Projects Organized

Scientific Computing in Python: Introduction to NumPy and Matplotlib

Interpretable Machine Learning

Chapter 1: Introduction to Machine Learning and Deep Learning

Book Review: Architects of Intelligence by Martin Ford

What's New in the 3rd Edition

My First Year at UW-Madison and a Gallery of Awesome Student Projects

Model evaluation, model selection, and algorithm selection in machine learning

Generating Gender-Neutral Face Images with Semi-Adversarial Neural Networks to Enhance Privacy

Model evaluation, model selection, and algorithm selection in machine learning

Model evaluation, model selection, and algorithm selection in machine learning

Model evaluation, model selection, and algorithm selection in machine learning

Writing 'Python Machine Learning'

Python, Machine Learning, and Language Wars

Single-Layer Neural Networks and Gradient Descent

Principal Component Analysis

Implementing a Weighted Majority Rule Ensemble Classifier

MusicMood

Turn Your Twitter Timeline into a Word Cloud

Naive Bayes and Text Classification

Kernel tricks and nonlinear dimensionality reduction via RBF kernel PCA

Predictive modeling, supervised machine learning, and pattern classification

Linear Discriminant Analysis

Dixon's Q test for outlier identification

About Feature Scaling and Normalization

Entry Point Data

Molecular docking, estimating free energies of binding, and AutoDock's semi-empirical force field

An introduction to parallel programming using Python's multiprocessing module

Kernel density estimation via the Parzen-Rosenblatt window method

Numeric matrix manipulation

The key differences between Python 2.7.x and Python 3.x with examples

5 simple steps for converting Markdown documents into HTML and adding Python syntax highlighting

Creating a table of contents with internal links in IPython Notebooks and Markdown documents

A Beginner's Guide to Python's Namespaces, Scope Resolution, and the LEGB Rule

Diving deep into Python

Implementing a Principal Component Analysis (PCA)

Installing Scientific Packages for Python3 on MacOS 10.9 Mavericks

A thorough guide to SQLite database operations in Python

Using OpenEye software for substructure alignments

Unit testing in Python

A short tutorial for decent heat maps in R

SQLite