Ahead of AI
https://magazine.sebastianraschka.com
Ahead of AI focuses on machine learning and AI research and is read by more than 200,000 researchers and practitioners who want to stay ahead in a rapidly evolving field. Click to read Ahead of AI, by Sebastian Raschka, PhD, a Substack publication with hundreds of thousands of subscribers.
フィード
Controlling Reasoning Effort in LLMs
Ahead of AI
How LLMs Learn Low-, Medium-, and High-Effort Reasoning Modes
1ヶ月前
Using Local Coding Agents
Ahead of AI
Using Open-Weight Models in Local Coding Harnesses as an Alternative to Claude Code and Codex Subscriptions
2ヶ月前
LLM Research Papers: The 2026 List (January to May)
Ahead of AI
A curated roundup of notable LLM research papers that came out this year
2ヶ月前
Recent Developments in LLM Architectures: KV Sharing, mHC, and Compressed Attention
Ahead of AI
From Gemma 4 to DeepSeek V4, How New Open-Weight LLMs Are Reducing Long-Context Costs
3ヶ月前
My Workflow for Understanding LLM Architectures
Ahead of AI
A learning-oriented workflow for understanding new open-weight model releases
4ヶ月前
Components of A Coding Agent
Ahead of AI
How coding agents use tools, memory, and repo context to make LLMs work better in practice
4ヶ月前
A Visual Guide to Attention Variants in Modern LLMs
Ahead of AI
From MHA and GQA to MLA, sparse attention, and hybrid architectures
5ヶ月前
A Dream of Spring for Open-Weight LLMs: 10 Architectures from Jan-Feb 2026
Ahead of AI
A Round Up And Comparison of 10 Open-Weight LLM Releases in Spring 2026
6ヶ月前
Categories of Inference-Time Scaling for Improved LLM Reasoning
Ahead of AI
And an Overview of Recent Inference-Scaling Papers
7ヶ月前
The State Of LLMs 2025: Progress, Problems, and Predictions
Ahead of AI
A 2025 review of large language models, from DeepSeek R1 and RLVR to inference-time scaling, benchmarks, architectures, and predictions for 2026.
7ヶ月前
LLM Research Papers: The 2025 List (July to December)
Ahead of AI
In June, I shared a bonus article with my curated and bookmarked research paper lists to the paid subscribers who make this Substack possible.
7ヶ月前
From DeepSeek V3 to V3.2: Architecture, Sparse Attention, and RL Updates
Ahead of AI
Understanding How DeepSeek's Flagship Open-Weight Models Evolved
8ヶ月前
Beyond Standard LLMs
Ahead of AI
Linear Attention Hybrids, Text Diffusion, Code World Models, and Small Recursive Transformers
9ヶ月前
Understanding the 4 Main Approaches to LLM Evaluation (From Scratch)
Ahead of AI
Multiple-Choice Benchmarks, Verifiers, Leaderboards, and LLM Judges with Code Examples
10ヶ月前
Understanding and Implementing Qwen3 From Scratch
Ahead of AI
A Detailed Look at One of the Leading Open-Source LLMs
1年前
From GPT-2 to gpt-oss: Analyzing the Architectural Advances
Ahead of AI
And How They Stack Up Against Qwen3
1年前
The Big LLM Architecture Comparison
Ahead of AI
From DeepSeek-V3 to Kimi K2: A Look At Modern LLM Architecture Design
1年前
LLM Research Papers: The 2025 List (January to June)
Ahead of AI
A topic-organized collection of 200+ LLM research papers from 2025
1年前
Understanding and Coding the KV Cache in LLMs from Scratch
Ahead of AI
KV caches are one of the most critical techniques for efficient inference in LLMs in production.
1年前
Coding LLMs from the Ground Up: A Complete Course
Ahead of AI
Why build LLMs from scratch? It's probably the best and most efficient way to learn how LLMs really work. Plus, many readers have told me they had a lot of fun doing it.
1年前