The Code Compass

How OpenAI Uses LLMs to Explain Neurons Inside LLMs

Explaining Neuron Behavior at Scale + Neuron Viewer

Sep 9, 2024 • 

CodeCompass

5

1

August 2024

How Google DeepMind's AlphaGeometry Reached Math Olympiad Level Reasoning By Combining Creative LLMs With Deductive Symbolic Engines

How open-sourced Neurosymbolic AI (Neural Networks + Symbolic Systems) is revolutionizing automated theorem proving

Aug 22, 2024 • 

CodeCompass

10

1

What is QLoRA?: A Visual Guide to Efficient Finetuning of Quantized LLMs

Sometimes smaller is better. How QLoRA combines efficiency and performance.

Aug 8, 2024 • 

CodeCompass

8

3

July 2024

[Jupyter Notebook] Build Your Own Open-source RAG Using LangChain, LLAMA 3 and Chroma

Constructing your local and zero cost RAG pipeline using free, open-source tools

Jul 23, 2024 • 

CodeCompass

11

2

What is Retrieval Augmented Generation? A Visual Guide On RAGs in the Context of LLMs

Without Fine-tuning, Integrate Custom Information and External Data Sources To Give LLMs Relevant Context To Hallucinate Less And Be More Accurate

Jul 11, 2024 • 

CodeCompass

16

2

4

Welcome to The Code Compass! [Start Here] ▶️

New to the newsletter? This post will help you get started and find your way around.

Jul 7, 2024 • 

CodeCompass

5

1

June 2024

Confident Product Decisions with Data: Inside Spotify’s Risk-Aware A/B Testing Framework

Learn how Spotify’s multi-metric evaluation strategy can enhance your A/B testing and drive innovative product decisions.

Jun 29, 2024 • 

CodeCompass

8

2

What is an Eigenvector?: A Visual Guide to This Fundamental Concept From Linear Algebra

Discover how eigenvectors can simplify complex data, enhance machine learning models, and solve real-world problems

Jun 20, 2024 • 

CodeCompass

9

2

What is LoRA?: A Visual Guide to Low-Rank Approximation for Fine-Tuning LLMs Efficiently

Why LoRA Is Essential For Model Fine-Tuning

Jun 13, 2024 • 

CodeCompass

13

3

Inside AlphaFold: DeepMind’s Recipe For Success

How To Build Teams Destined For Breakthroughs

Jun 6, 2024 • 

CodeCompass

8

3

May 2024

The Challenges of Building Effective LLM Benchmarks

Current state of LLM evaluation and gaps that need filling with comprehensive and high quality leaderboards

May 30, 2024 • 

CodeCompass

4

2

Why You Should Not Strive For Perfection: Perfect is the Enemy of Good

How Perfectionism Slows Down Software Development Progress And How To Avoid It

May 23, 2024 • 

CodeCompass

3

2