HNSW - Finding Needles in Vector Haystacks

On the cover: HNSW graph depiction. Credits: Marqo Imagine a city with 10 million coffee shops. You (the customer) have a very specific taste vector: medium roast, cozy seating, quiet music. Now how do you go about finding the best coffee shop? ...

Padlocks to Prime Numbers - RSA Encryption and SSH

On the cover: RSA Encryption If you’ve ever shopped online, sent a private message, or connected to a secure website, you’ve probably used RSA encryption without even knowing it. RSA was founded by three mathematicians Rivest–Shamir–Adleman (RSA)...

How can you cook your pasta fasta? :p

On the cover: A cute robot chef cooking pasta Concurrency in Python is like running a restaurant kitchen during a dinner rush - and if you’re making pasta, you’re bound to get a side of judgment from an Italian grandma every time you mess up. Le...

LoRA - The Diet Pill for Obese Language Models

On the cover: The concept of low-rank adaptation visualized as dimension reduction If you’ve been paying any attention to the AI world lately, you might have noticed these large language models (LLMs) getting increasingly heavy and fat. GPT-4 is ...

Flux Models: The New Kid on the Generative Block - Part 2

On the cover: An AI-generated image showcasing the capabilities of Flux models In Part 1 of this series, we explored the basics of Flux models, their mathematical foundations, and how they compare to traditional diffusion models. Now, let’s dive ...