Recent posts
Have you ever had an idea, researched it and then discovered that it already exists in the form of an app, website, physical product, etc.? Did you then get discouraged? Rather than being discouraged, you should be motivated. Why? You have proof that the idea works. Novel ideas are risky because the…
I've been using Nim for about 1-2 years now, and I believe the language is undervalued. It's not perfect, of course, but it's pleasant to write and read. My personal website uses Nim. After reading a recent article on Nim ("Why Nim") and the associated HN comments, it's clear that comments and some…
tl;dr Despite their name, decoder-only Transformers (M-LLMs, e.g. Llama, Mistral, Qwen, etc.) can be fine-tuned into an encoder to obtain embeddings for retrieval tasks, e.g. RAG, semantic search, etc., which can achieve state-of-the-art (SoTA) results You can have your cake and eat it too: the same…
Introduction Here is advice I've collected from others and myself over the years, which serves as a set of guidelines when attempting to do "The Thing". The Thing is anything, however this article is biased toward software development, but it does apply to other "Things" in life. 1. What Should You…
Introduction This is a filtered curation of papers that I found over the years that either inspire me, blow me away (revolutionize the way I think) or are an essential read for someone within the field. Some of these papers I have not personally read in detail. I have also included a section on lear…
Introduction I stumbled across an interesting paper, which shows that you can multiply two numbers by using the Collatz conjecture (and assuming it to be true for the numbers you are dealing with). This post contains my summary and understanding of how this method works. Background Collatz conjectur…