Davo, Author at Dave Tang's blog

15th Anniversary

AnnouncementDavoOctober 1, 20250

It has been 15 years since I started this blog! As typical with many of my anniversary posts, I reflect on things that I have started to do and/or have learned since the last time I wrote an anniversary post. Here’s the full collection of anniversary posts from past years: https://davetang.org/muse/2014/10/01/4th-anniversary/ https://davetang.org/muse/2015/10/02/5th-anniversary/ https://davetang.org/muse/2016/09/30/6th-anniversary/ https://davetang.org/muse/2017/10/01/7th-anniversary/ https://davetang.org/muse/2020/10/01/ten-years/…

On professionalism

/etcDavoAugust 30, 20250

I’m a huge fan of Conan O’Brien; there’s just something about his demeanour, humour, and wittiness that I admire. I discovered him on YouTube around 2012 and was quite oblivious to who he was, what he believed in, and what he had done; for example, I never realised that he produced and/or wrote some of…

Hosting your own Git repositories

GitDavoAugust 14, 20250

As you may have already heard, GitHub just got less independent at Microsoft after CEO resignation. What does this mean? Well, I guess nobody knows for certain but it probably will mean that GitHub would degrade as a service. As a business, profit and growth are the main focus of Microsoft, so everything else becomes…

How long does it take to run gpt-oss:20b?

funDavoAugust 10, 20250

gpt-oss is OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. You can easily use it via Ollama and read more about it in their blog post. Let’s see how long it takes to generate some output using the same prompt on some of my computers at home. For this…

Retrieval-Augmented Generation

funDavoMay 27, 20250

Back in February I learned about Open WebUI and have been wanting to test it out with Retrieval-Augmented Generation (RAG). I’ll follow the tutorial available on Open WebUI’s site. The goal of RAG is to provide Large Language Models (LLMs) with specific information with the goal of improving the output. My main interest in RAG…

One tip per day

TILDavoMay 14, 20252

I have been adding one tip per day to my daily tips GitHub repo for the past month. It’s a simple setup: I manually add tips to a YAML file I use a Python script to convert YAML to Markdown A helper script appends the Markdown file, README.md, with today’s tip I’ve also set up…

Doing the same thing over and over

museDavoApril 24, 20250

There’s this quote that is commonly attributed to Albert Einstein (though it’s uncertain whether he really said it or not): Insanity is doing the same thing over and over again and expecting different results. I first came across it a long time ago, when I was much less discerning. After reading it, I envisioned someone…

Git stash

GitDavoMarch 31, 20250

TL;DR Use git stash to stash changes. Update from remote using git pull. Apply stash changes to latest changes using git stash pop. If there’s a merge conflict, manually resolve using some text editor like Nvim. Changes from upstream and stash are demarcated with angle brackets. After resolving, add, commit, and push! Clean up stash…

Thoughts on AI

museDavoMarch 7, 20250

I have been interested in machine learning since I was a PhD student back in 2010. I was always in awe of papers where they applied machine learning to cluster or classify data. My original PhD topic was to discover biomarkers in blood for Parkinson’s Disease (PD) patients that were early onset and had not…

TIL about Open WebUI

TILDavoFebruary 28, 20250

I just heard about Open WebUI from Harish’s comment on my Ollama and DeepSeek post and decided to check it out. From their website: Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform designed to operate entirely offline. It supports various LLM runners like Ollama and OpenAI-compatible APIs, with built-in inference engine for…