Cybernetist

You Should Probably Pay Attention to Tokenizers

Mon, 21 Oct 2024 07:57:33 +0100

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.

Some Notes on Adversarial Attacks on LLMs

Mon, 23 Sep 2024 07:57:33 +0100

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.

My Three Favorite Scenes From The Bear

Mon, 24 Jun 2024 17:01:48 +0100

I heard about The Bear TV show from my brother a few times over the past couple of years but I never really felt like watching it. A TV show about a frantic family-run bistro in Chicago? Color me sceptical. Don’t get me wrong, I’ve got nothing against the catering or hospitality industry! My brother is a restaurant manager and I spent a fair amount of my youth cleaning dishes at many dubious establishments over a few summers before I learnt to make money by doing things with computers.

Using Cuelang With Go for LLM Data Extraction

Mon, 13 May 2024 01:57:54 +0000

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.

Go or Rust? Just Listen to the Bots

Thu, 25 Apr 2024 08:21:47 +0100

It all started as a joke. I was in a group chat with a few of my friends and we were talking about football (soccer for the American readers). I entered the chat during a mildly heated discussion about the manager of a team one of my friends supports. It was going on for a bit while with seemingly no end in sight when it occurred to me that I could just as well clone my friends’ voices and pit them against each other by backing them with LLMs, and I’d probably not see much difference in the conversation.

Builders Are Happier But What Happens When AI Takes Over

Mon, 22 Apr 2024 18:23:24 +0100

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.

Rust tokio task cancellation patterns

Fri, 19 Apr 2024 09:00:10 +0100

Update: 19/04/2024: read at the end of the post for more info.

I have been trying to pick up Rust again recently. It’s been a bit of a slow burn at the beginning but I think I’m finally starting to feel the compounding effects kicking in. Maybe it’s just my brain playing a trick on me, but I’m feeling at much more ease when writing Rust now than I was a few weeks back.

Circular Buffer Performance Trick

Thu, 11 Apr 2024 10:00:10 +0100

Update 12/04/2024: Read at the end of the post for more info.

I have been hacking on AI agents recently for both fun and profit as part of the work I’m doing for one of my clients.

They’re mostly text-to-speech (TTS) agents leveraging LLMs for generating text which is then turned into voice by a trained TTS model.

As you [probably] know, maintaining conversation with LLMs over a longer period of time requires maintaining the conversational context and sending it back to the LLM along with your follow-up prompts to prevent the LLMs from “hallucinating” from the get-go.

A Small Tool for Exploring Text Embeddings

Wed, 27 Mar 2024 09:48:26 +0000

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.

On The Importance of Getting The Foundations Right

Mon, 11 Mar 2024 19:14:37 +0000

Throughout my career, I’ve learnt, usually the hard way, the importance of getting the foundations of whatever I was working on right. Or at least as right as possible. I learnt how fundamental it is for setting your project — and by proxy, your team — up for success. I’d argue it’s one of the most important things you should pay attention to. Getting the basics right is notoriously hard due to the inevitability of changing requirements, external factors, etc. which is why dedicating a reasonably large amount of time to figure out the foundations is so invaluable.

Fun With AI Embeddings in Go

Sun, 07 Jan 2024 11:48:26 +0000

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.

Some [career] advice for engineers

Sun, 05 Nov 2023 11:06:31 +0100

This blog post is a collection of advice or rules I’ve learnt to live by as a software engineer.

It’s an accumulation of experiences I’ve gained through working for software organizations of various sizes.

Most of the advice in this post is aimed at software engineers, but some may be applicable to other roles and industries.

Understand the problems you are solving

This isn’t a revolutionary idea. But the very sad reality of life is that it still hasn’t been internalised by so many engineers and organisations that it’s worth reiterating. I can’t stress enough how important understanding the problems you are trying to solve is. I’ve seen countless hours and budgets wasted on “solving” problems that have been completely misunderstood and often actually made worse by taking the wrong action.

A Few Counterintuitive Ideas

Sat, 01 Jan 2022 08:44:01 +0100

UPDATE: 4th January, The way out of burnout

The beginning of 2021 marked the point when some of us were bracing with hope for the year that lied ahead. The year that we hoped to be “better” than the one that we were leaving behind. Little did we know we should have braced for impact instead.

For me personally, if 2020 was bad enough then 2021 wiped the last shreds of whatever mental resilience or energy I had left in me. I’m entering 2022 pretty much on some kinda pandemic cruise control. Time as measured by calendar days no longer matters, the majority of the human contact happens over bits and bytes and, yet, “things” can still get worse. They call it the “new normal”. Whatever. At least I’ve survived so I got that goin’ for me which is nice.

Getting Started With LDAP in Go

Mon, 18 May 2020 19:43:12 +0100

Recently I had to write a fair amount of Go code which interacts with Active Directory (AD) for one of my clients. AD uses Lightweight Directory Access Protocol (LDAP) [1] for client-server communication. LDAP is a very mature and powerful protocol to interact with directory services, though some of my friends argue that it’s a bit of a relic of past at this point. I disagree with this sentiment, but my explanation why would probably take a whole another blog post.

Build a Graph of Kubernetes API Objects in Go

Sun, 03 May 2020 10:11:53 +0100

Over the past few months, I have been rekindling my interest in graph theory. I’m not quite sure what has caused this shift in my mind as I didn’t play with graphs too much since I graduated many moons ago, besides the occasional interview preparation. Maybe it was my reading about all the new graph databases that have come to existence over the past few years, or maybe it was my interest in the Graph Neural Networks which also seem to have (re)gained a lot of attention in the research community or maybe, stimulated by the recent coronavirus outbreak, it was the result of my random thinking of the ever so increasingly interconnected nature of our world.

Happy 5th Birthday Kubernetes London

Sat, 21 Mar 2020 18:55:08 +0000

On 26th March Kubernetes London Meetup planned to host another event. It was supposed to be our 5th birthday so we had worked hard to make the event, to quote Kelsey Hightower, “Dope”. Unfortunately, it wasn’t to be as the coronavirus disrupted all levels of public life in a way our generation never experienced before.

This blog post is the long version of the short talk I wanted to give at the event to walk through some of the most memorable experiences I’ve had in the past 5 years as one of the Meetup organizers.

Swift ARKit Sun iPhone App for Londoners

Mon, 17 Feb 2020 15:04:37 +0000

If you happen to be one of the lucky people living in London you couldn’t miss we’ve had a bit of a sunlight crisis [not just recently]. Instead of the usual vitamin D deficiency which we are used to being brought to our attention during regular health checks things have been a little bit worse than that. First we got a visit by storm Ciara which was then shortly followed by storm Dennis. What do you do when the only sunlight you can get is watching David Attenborough documentaries on Netflix? You guessed it! You build an ARKit app in Swift which lets you put the fiery sphere [not just] in your room. Now you can get sunlight whenever you need it, wherever you are! Just tap the screen and off you go! You can find the full implementation of the app on GitHub.

Breadth-first search using Go standard library

Mon, 02 Sep 2019 23:28:55 +0000

Just like many Go developers out there, I’m a big fan of Go standard library. Over the past few years I’ve been hacking on Go, I’ve discovered some real gems that not only made my life as a developer easier (no need to maintain unnecessary code), but they also made my code considerably more readable for others to follow. The last time I blogged I talked about how you can leverage Go standard library to generate weighted random draws.

WASM: Universal Application Runtime

Thu, 25 Apr 2019 13:02:40 +0000

WASM: universal application runtime

Last summer, fresh off my last freelance gig, I was catching up with my friend Asim, the founder of the widely popular microservices company, Micro at one of our favourite coffee shops in London. We would end up meeting almost every week talking about the presence and the future of technology. But that day our conversation turned into something that we had not talked about for a long time: Web assembly (WASM).

Weighted Random Draws in Go

Thu, 24 Jan 2019 17:42:48 +0000

When working on my last project I needed to find a way to draw a random number from a list based on some weight assigned to it i.e. given a list of numbers each of which has a weight assigned to it, I had to find a way to draw a number from the list based on the weight. The numbers which have higher weight assigned to them should be more likely to be drawn than the numbers with lower weights.

Apollo program, Kalman Filter and Go

Sun, 13 Jan 2019 22:53:08 +0000

Before the end of the last year I went to see a movie made by one of my favourite movie directors, Damien Chazelle. The movie is called First Man and it tells the story of the journey of the first man on the Moon. I am also a bit of a space nerd, so my expectations were sky high. I was happy to find out the movie delivered on its promise.

What I liked about it the most was that it showed the [human] sacrifice that had to be made in order to achieve, what has arguably been one of the biggest achievements of humankind to date. Many lives were ruined [and lost] in the pursuit of greatness and place in the history. Astronauts would compete with each other for the spots on the spaceships in spite of knowing they might not return back to Earth at all. Besides every [technological] achievement there is a price to pay. Some are high, others are higher. This was the golden era of space exploration, the era when the geopolitical tensions around the world were immense.

Edge computing with Go and Intel Movidius Neural Compute Stick

Sun, 07 Oct 2018 17:23:08 +0000

This summer I spent quite a bit of time speaking to various people about “intelligent” Edge computing. I put double quotes around the word intelligent to avoid the wrath of the thought leaders on the internet as they fight each other over what intelligence is and what is not.

The more I talked to people the more I was realizing the possibilities and opportunities the edge computing opens up for the future: “injecting” intelligence into dumb physical objects seems akin to injecting “life” to dead objects, at least for us, scifi fans, which makes up for interesting vision of the future (for brevity let’s ignore the IoT security issues in this post). The possibilities are even more exciting in light of machine learning and neural networks models getting lighter and more easily deployable in the physical space. And let’s not forget about all the efforts to bring intelligence into some variation of IoT blockchain.

Tensorflow conditionals and while loops

Tue, 27 Mar 2018 01:57:54 +0000

Tensorflow conditionals and while loops

Recntly I found myself needing to implement more advanced control flow in some models I have been hacking on in my free time. In past I never really needed any graph conditionals or loops or any combinations thereof, so I had to dive into documentation and read up on them.

This blog post covers tf.cond and tf.while_loop control flow operations and was written to document and share my experience learning about them. Both of the operations seem intuitive on the first look, but I got bitten by them so I wanted to document their usage on practical examples so I have something as a reference I can return to in the future should I need to.

Hopfield networks in Go

Sun, 12 Mar 2017 22:12:58 +0000

As I continue to explore the realm of Artificial Neural Networks (ANN) I keep learning about some really cool types of neural networks which don’t get much attention these days. Many of these networks have not found much practical use in the “real world” for various reasons. Nevertheless, I find learning about them in my free time somewhat stimulating as they often make me think of some problems from a different perspective. One such ANN is called Hopfield Network (a.k.a. Hopfield net), named after its inventor John Hopfield.

Kubernetes services and ingress under X-ray

Mon, 30 Jan 2017 13:03:04 +0000

I haven’t blogged here for over 2 years. It’s not that I had nothing to say, but every time I started writing a new post I never pushed myself into finishing it. So, most of the drafts ended up rotting in my private Github gists. Although my interests have expanded way beyond the Linux container space, my professional life remained tied to it.

Over the past two years I have been quite heavily involved in Kubernetes (K8s) community. I helped to start Kubernetes London Meetup as well as Kubecast, a podcast about all things K8s. It’s been amazing to see the community [not only in London] to grow so fast in such a short time.

Self-organizing Maps in Go

Fri, 13 Jan 2017 11:22:59 +0000

Couple of months ago I came across a type of Artificial Neural Network I knew very little about: Self-organizing map (SOM). I vaguely remembered the term from my university studies. We scratched upon it when we were learning about data clustering algorithms. So when I re-discovered it again, my knowledge of it was very basic, almost non-existent. It felt like a great opportunity to learn something new and interesting, so I rolled up my sleeves, dived into reading and hacking.

Fun with neural networks in Go

Wed, 27 Jul 2016 11:00:31 +0000

My rekindled interest in Machine Learning turned my attention to Neural Networks or more precisely Artificial Neural Networks (ANN). I started tinkering with ANN by building simple prototypes in R. However, my basic knowledge of the topic only got me so far. I struggled to understand why certain parameters work better than others. I wanted to understand the inner workings of ANN learning better. So I built a long list of questions and started looking for answers.

Principal Component Analysis - Part 2

Wed, 20 Apr 2016 22:24:53 +0000

This is the second post of the series about Principal Component Analysis (PCA). Whilst the first post provided a theoretical background, this post will discuss the actual implementation of the PCA algorithm and its results when applied to some example data.

Theory Recap

In the first post we learnt that PCA looks for a vector basis that can express the analysed data in a better (less redundant) way, whilst retaining as much information from the original data as possible. The vectors that form this vector basis are called principal components.

Principal Component Analysis - Part 1

Tue, 12 Apr 2016 11:46:42 +0000

This is the first of the two post series about Principal Component Analysis (PCA). This post lays down important knowledge bricks that are needed to understand the core principles of the PCA algorithm. The second post will discuss the actual implementation and its results by applying it to various data sets.

Motivation

The world is becoming more data driven than ever before. We collect large amounts of data from arbitrary sources. This is often because we don’t know which data best describes the systems we are trying to understand. The fear of missing out on capturing important features forces us to collect a lot of redundant data.

Docker vs Rocket gimme a break

Fri, 19 Dec 2014 17:11:28 +0000

Alert! This is another rant blog post! I promise the next one will be more technical :-)

Rocket launch me some opinions

Past few days I’ve been playing around with Rocket, the new container runtime by CoreOS. Quite a few people have asked for my opinion so I figured I would put it into a blog post. I haven’t planned on publishing it any time soon, but few blog posts I have come across recently have prompted me to put off the original post and write a different one first. So before I finalise I need to get something out of my chest first. Anyhow, let’s get to it!

Future of Docker networking

Tue, 11 Nov 2014 01:03:28 +0000

Disclaimer: I do not work for Docker nor for any company whose business is tied to Docker in any way

Recently there has been a lot of discussions about the future of Docker networking in various communication channels. It is due to hugely increased Docker usage over the past year. Users are now realising Docker’s networking limitations which are becoming more apparent. The truth is, and I’m sure we can all agree on this, the current networking capabilities of Docker are not sufficient for more complicated setups. Current model is plagued with performance issues and not flexible enough. But for a basic usage it does a pretty good job. However, we never just stay within “basic usage” realm. With the cloud and current world of microservices this is almost impossible. So the time has come to move forward. As one of many contributors to libcontainer, I feel like I need to express my opinion about where I stand in all these discussions and this blog post is about that.

Tenus Golang Powered Linux Networking

Wed, 30 Jul 2014 12:13:44 +0000

2014-07-30 22:35 Update: I’ve updated the post with the link to netlink RFC. I’ve also replaced references to golang with Go programming language on majority of mentions in the article. I do agree with the people in discussions on the topic of Go/golang, but I’ve adpoted golang in my vocabulary as that’s my standard search term on Google for the information about Go language, hence the abundance of the word golang in the original post.

Exploring LXC Networking

Tue, 19 Nov 2013 10:14:28 +0000

Daily Dilemma

Recently I’ve been finding myself in various conversations about Docker and Linux Containers (LXC). Most of the time the conversations eventually end up with one and the same question and that is whether we should run containers in production. Initially this post had a few paragraphs where I philosophised about readiness of the technology, but I’ve deleted those paragraphs now as the attention dedicated to containers in past year has been nothing short of amazing and more and more companies are running their Infrastructures in the containers or at least big parts of them. I’m sure this trend will continue to high degree in the future, so I’ve now removed these paragraphs and kept the technical content only.

About me

Sun, 10 Nov 2013 02:46:32 +0000

My name is Milos. I’m a software engineer currently living in London, UK. I graduated from Czech Technical University in Prague with Masters degree in Technical Cybernetincs, which is a fancy word that encompasses machine learning, control engineering and artificial intelligence.

I’m one of the authors of a small book about Docker. I started Kubernetes London Meetup, currently one of the largest Kubernetes Meetups around the world, though I stepped down as an organiser in 2023 to free up some of my time. Most recently I worked as a Tech Lead on Docker Hub. I am one of the maintainers on the OSS registry aka distribution. In the past I also worked on one of the most popular Go microservices frameworks (see my contributions here).

Let's Work Together

Sun, 10 Nov 2013 02:46:32 +0000

I am always open to new interesting opportunities.

My current areas of interest are Go, AI agents and recently Rust. I enjoy all aspects of backend engineering and I’m no stranger to frontend either.

If you work on anything interesting in these areas we should work together! Drop me an email to my GitHub email address.

You can read about me here and find out about my OSS work on my GitHub.

Mon, 01 Jan 0001 00:00:00 +0000