The blog post explains differences in access, licensing, size, context length, and language/domain of Large Language Models (LLMs) for developers and users to navigate the LLM landscape effectively.

I used unsupervised methods to try and construct the phrase “wash your hands” in 510 languages not currently supported in any public translation platform.

There are a wide variety of techniques to employ when trying to create a new machine translation model for a low resource language or improve an existing baseline.

Linear regression and gradient descent are techniques that form the basis of many other, more complicated, ML/AI techniques (e.g., deep learning models). They are, thus, building blocks that all ML/AI engineers need to understand.

I decided that I would build a neural network from scratch in Go. Turns out, this is fairly easy, and I thought it would be great to share my little neural net here.