Moritz's AI blog

Moritz's AI blog

Home
Notes
Archive
About

May 2024

March 2024

How to run CUDA in a Colab notebook
Develop and test high-performance CUDA applications directly within a browser, without the need for local GPU resources.
 • 
Moritz Strube
What does 1 million tokens mean for LLMs?
A significant leap forward in the development of LLMs.
 • 
Moritz Strube
Deep Learning's Rise, Reality, and the Road Ahead
The development and current state of Artificial Intelligence (AI), especially in the realm of Deep Learning, demonstrates both impressive successes and…
 • 
Moritz Strube
Accessing Google's LLM Gemini Pro
Recently Google announced the publication of the LLM Gemini Pro, which outperformed GPT-3.5 in six out of eight benchmarks. In this post I describe…
 • 
Moritz Strube
How does RLHF work?
Understanding Reinforcement Learning from Human Feedback (RLHF) in detail without getting too technical.
 • 
Moritz Strube
Embeddings for LLMs and cosine similarity explained
A not too technical overview of how to map arbitrary length texts to fixed length vectors and translate semantic similarity into distances in a vector…
 • 
Moritz Strube
Does the example of Klarna indicate the beginning of a quaternary sector in the economy?
Economic activities have traditionally been categorized into three distinct sectors: primary, secondary, and tertiary. In this article, we look at the…
 • 
Moritz Strube
Access the OpenAI API with curl
This is a simple tutorial that shows you how to access the OpenAI API with curl, an easy-to-use command line tool. A first step towards integrating LLMs…
 • 
Moritz Strube

February 2024

© 2025 Moritz Strube
Privacy ∙ Terms ∙ Collection notice
Start writingGet the app
Substack is the home for great culture