Last week I was helping a friend of mine to get one of his new apps off the ground. I can’t speak much about it at the moment, other than like most apps nowadays it has some AI sprinkled over it. Ok, maybe a bit maybe more just a bit – depends on the way you look at it, I suppose.

There is a Retrieval-augmented generation (RAG) hiding somewhere in most of the AI apps. RAG is still all the RAGe – it even has its own Wikipedia page now! I’m not sure if anyone is tracking how fast a term reaches the point where it gets its own Wiki page but RAG must be somewhere near the top of the charts.

Intro

Last week I was catching up with one of my best mates after a long while. He is a well-recognised industry expert who also runs a successful cybersecurity consultancy. Though we had a lot of other things to catch up on, inevitably, our conversation led to AI, LLMs and their (cyber)security implications.

I’ve spent the last couple of months working for early-stage startups building LLM (Large Language Model) apps, as well as hacking on various silly side projects which involved interacting with LLMs in one way or another. But only now I’m starting to realize how naive some of the apps I have helped to build were from the security [and safety] point of view.

I have been aware of Cuelang (CUE) pretty much since the early stages of its development. It always seemed to me the language had the potential to solve a lot of problems in the ocean of YAML which we found ourselves drowning in the Cloud Native ecosystem.

CUE excels in validating data against strictly defined schemas and is equally capable of generating code for data models from them. These are wonderful features, though I hadn’t found the perfect application for them in any of the projects I had been working on. That changed recently with my increased involvement in projects utilizing Large Language Models (LLM)s.

I have been busy hacking since I got back from my long holidays. I didn’t miss computers while travelling around the world. Not for a second. When you hike up a volcano and engorge yourself in the beautiful views only this planet can reward you with it’s hard to think of computers let alone hacking.

But now that I’m back and re-engaged my hacking mode I’ve gained a whole new appreciation for what the act of building software gives me. I like building things. Silly things. Any things. It’s fun. I find it engaging and fulfilling for reasons I don’t quite fully understand. To be honest, I’ve never really thought about the reasons. Is it the dopamine I get from solving problems with code? Is it the feeling of accomplishment? Is it just the IKEA effect at play? I don’t know. Frankly, I don’t really care that much about the actual reasons behind it. It’s the effect the activity has on me what matters.

Last year I wrote about the superpowers text embeddings can give you and how I tried using them to compare the song lyrics of some music artists. Though the results failed to paint the picture I hoped for – this was due to the methodology, or rather lack thereof – it made me appreciate the importance of simple open source tools (OSS) in the currently booming AI/LLM space.

To get to the point of displaying the embedding projections in the blog post I had to jump through some hoops and combine a lot of different Go modules before I could finally generate the nice interactive plots from the computed data. This wasn’t ideal I knew even back then but I wrote a blog post on a whim trying to quickly prove a silly point to a friend of mine. So at the time, I made do with whatever was necessary.

Update 9th January, 2024: Changed the title to “Fun With AI Embeddings in Go”

Before the end of last year, I visited San Francisco (SF) for a few weeks. It felt great meeting some old friends and ex-colleagues face-to-face after a long hiatus. There is something incredibly refreshing about being in the same room with the folks you’ve spent chatting to so much time over the past few years on Zoom or Slack. Real-life connections remain undefeated and I hope it will stay that way.