In the previous installment of the ongoing desk treadmill experiment (linked below), I mentioned that the circumstances of the treadmill I use today was probably not what the sane person would have done.
Rather I honestly had no intention of starting this experiment this year. Instead this experiment was a result of being in the right place at the right time and keeping the spirit of tinkering alive.
Right Place
With my “Always Tinkering” mindset, I was browsing the marketplace one weekend and decided to browse the offerings for treadmills. More of a fluke than anything I found a listing for an Under Desk Treadmill at the price of $0 with a description that it turns on but displays an error.
KubeCon and CloudNativeCon North America 2023 is fast approaching. It is without contest my favorite event of the year.
What I wanted to do was outline some tips for everyone - from first time attendees to experienced attendees - for what I believe contributes to a great event.
Situational Awareness
First an foremost do some logistical planning:
How far are you from the venue?
What will you need to bring based upon that?
What all do you have have planned that may change what you need?
Rarely has the venue ever been hot - and we’re talking November in Chicago so a warming layer may not be a bad idea.
When I set out to created this blog, as noted in my Blogging the hard way article, I had a couple key objectives that I wanted to pursue:
Reproducible and static
Meaning highly portable
Minimal configuration required
Markdown content and generate
And most importantly - Open - as in anyone can look at the repository and see every single detail that makes this site run. If I inspire even one person to have some fun exploring Hugo and the adventure that is serving content to the world from the comfort of their own home - then I’d call it a success.
For those are are emerging into the AI space later than others - like myself - I found the prospects and Retrieval-Augmented Generation (RAG) to be a great capability. RAG is not new but it connects from of the underlying AI magic to decision making that makes sense.
The missing piece? Context/Background.
Retrieval-augmented generation in Language Models (LLMs) is a framework that combines the capabilities of both retrieval models and generative models to improve the quality and relevance of generated text. This approach aims to enhance the generation process by incorporating information retrieved from external sources during text generation.
Tabby is a self-hosted AI coding assistant, offering an open-source and on-premises alternative to GitHub Copilot.
HomeLab
For those who haven’t read my previous review of FauxPilot, I have been experimenting with Open Source CodeGen AI for the last few months. Using an old desktop I convert to Proxmox, I dedicated my RTX 2080 to an Ubuntu VM that is my current test-bed for AI code generation tooling.
