Everything you care about in one place
Follow feeds: blogs, news, RSS and more. An effortless way to read and digest content of your choice.
Get Feedersebastianraschka.com
Sebastian Raschka's Website
Get the latest updates from Sebastian Raschka's Website directly as they happen.
Follow now 62 followers
Latest posts
Last updated 4 days ago
From Random Forests to RLVR: A Short History of ML/AI Hello Worlds
5 days ago
Two years ago, I posted a list of Hello World examples for...
A Technical Tour of the DeepSeek Models from V3 to V3.2
10 days ago
Similar to DeepSeek V3, the team released their new flagship model over...
Recommendations for Getting the Most Out of a Technical Book
about 1 month ago
This short article compiles a few notes I previously shared when readers...
Beyond Standard LLMs
about 1 month ago
After I shared my Big LLM Architecture Comparison a few months ago...
DGX Spark and Mac Mini for Local PyTorch Development
about 2 months ago
The DGX Spark for local LLM inferencing and fine-tuning was a pretty...
Understanding the 4 Main Approaches to LLM Evaluation (From Scratch)
2 months ago
Multiple-Choice Benchmarks, Verifiers, Leaderboards, and LLM Judges with Code Examples
Understanding the 4 Main Approaches to LLM Evaluation (From Scratch)
2 months ago
Multiple-Choice Benchmarks, Verifiers, Leaderboards, and LLM Judges with Code Examples
Understanding and Implementing Qwen3 From Scratch
3 months ago
Previously, I compared the most notable open-weight architectures of 2025 in The...
Understanding and Implementing Qwen3 From Scratch
3 months ago
Previously, I compared the most notable open-weight architectures of 2025 in The...
From GPT-2 to gpt-oss: Analyzing the Architectural Advances
4 months ago
OpenAI just released their new open-weight LLMs this week: gpt-oss-120b and gpt-oss-20b...
From GPT-2 to gpt-oss: Analyzing the Architectural Advances
4 months ago
OpenAI just released their new open-weight LLMs this week: gpt-oss-120b and gpt-oss-20b...
The Big LLM Architecture Comparison
5 months ago
It has been seven years since the original GPT architecture was developed...