Optimizing RAG to Search 36 Million PubMed Articles in Milliseconds Instead of Minutes

June 28, 2024

Are LLMs useful because they overfit everything?

June 4, 2024

and should we care ...

Approximate Binary Vector Search for RAG in Julia

May 28, 2024

State-of-the-Art Exact Binary Vector Search for RAG in 100 lines of Julia

May 16, 2024

LLMs: Context Matters. A LOT.

April 4, 2024

How To Do A Landing Page Fade-In

March 13, 2024

Generative AI vs. AWS Textract: A Case for GPT Wrappers.

March 4, 2024

In this edition of GPT Wrappers Eat Software ...

LLMs can dream of electric sheep, but can they add?

February 16, 2024

No. a + b is hard man.

On LLM Writing

December 9, 2023

Type like a monkey and get Shakespeare (kinda)

Counting nanoGPT FLOPs in PyTorch

October 26, 2023

it works!

Rough Notes: Deep Learning From The Ground Up

September 3, 2023

grab a shovel


March 21, 2023

grok grok grok

Meta-Learning with Julia & Flux

February 2, 2019

Learning to learn things fast!

The Case of the Doomed Agent

July 11, 2016

Deep Reinforcement Learning on Doom simulations.

Memory Networks

December 21, 2015

What was I supposed to write here again?