Artificial Intelligence
Our team set out to investigate if we could use Binoculars, a method of detecting LLM-generated text, to detect AI-written code, and learnt some valuable lessons on the importance of data quality along the way.
Artificial Intelligence
As the government progresses from prototype to production to ongoing operation with AI-assisted services for UK citizens, how can it minimise the risk of replicating structural biases? In this blog post, I’ll explore key elements of what’s involved in ensuring that services are as representative, fair and impartial as possible.
Artificial Intelligence
I reflect on recent discussions with civil servants and our own research to consider how AI might increase productivity and offer new capabilities. At the same time, I’ll explore the necessary checks and balances on how far AI should be applied in delivering services to UK citizens.
Artificial Intelligence
Data is important to every element of the safe and successful harnessing of AI. For the government, data challenges are not new, nor are they insurmountable. In this post, I’ll look at some of those challenges across the data lifecycle, and share insights from our recent work and conversations with government about practical ways forward.
Sustainability
This is the second of a series of blog posts that examine the various methods of measuring carbon emissions on end-user devices. In this post, we look at methods and tools for power profiling and measuring the energy use of devices with a bottom-up approach.
Podcast
In this episode, I'm joined for a discussion on observability by Scott Rowan, Senior Developer at Scott Logic, and Daniel Gomez Blanco, Principal Engineer at Skyscanner. Our conversation explores what observability means in modern distributed software architectures, how it differs from traditional monitoring, and the challenges of implementing observability at scale.
Artificial Intelligence
Government departments are not alone in struggling to move artificial intelligence (AI) prototypes into production. Here, I reflect on some of the reasons for this and share some insights from our client work which I think point towards how the government can harness AI with greater confidence.
Delivery
We often talk about how to be agile, about particular ceremonies and processes but what problem is it we are trying to solve? In this post I'll take a look at what we mean when we talk about agile, what it's come to represent and what the point is behind aiming for agility.
Tech
Mobiumata (a concatenation of Möbius strip and cellular automata) is a small interactive art piece that allows folk to play god to 1,500 LED cells wrapped into a Möbius strip.
Testing
Many organisations mistakenly think Behaviour-Driven Development (BDD) is simply about writing test cases in Given-When-Then format or using test automation frameworks. While automation is a valuable by-product, the true essence of BDD lies in enhancing team collaboration and understanding business requirements. BDD includes three practices- discovery, formulation, and automation, with the discovery phase being foundational. Adhering to best practices ensures that BDD scenarios are clear, focused, and valuable, ultimately creating living documentation that accurately reflects the system's behaviour.
Artificial Intelligence
Generative AI has a Sustainability problem – across environment, cost and continuing to meet expectations. Many companies are racing to implement GenAI in their projects, lured by its hyped potential to revolutionise industries. However, in applying GenAI to enterprise implementations, I am seeing first-hand the sustainability challenges threatening to implode the first generation of this technology. This blog talks about what I hope will rise from the ashes of such an implosion.
Artificial Intelligence
Many of us are now using Generative AI to produce code, but what impact is this having on code quality? By analysing the data contained in PRs, our team has built a tool to investigate this.
Artificial Intelligence
As we keep on building the InferGPT chatbot, the task of crafting prompts is one that our team is experimenting with. In this blog I'll explore some of the challenges of prompt engineering from a Linguistics angle.
Open Source
It seems barely a month goes by without a new supply chain attack making the headlines, and malicious code in dependency packages from package managers such as NPM is a common method. My usual sentiments include “oh another one, what a surprise”, before thoughts eventually turn to - someone *really* ought to be doing something about this. Fortunately, it turns out that quite a few things are indeed being done - there's progress, activity, and promising ideas for the future. The outlook is brighter than what we might have assumed.
Podcast
In this episode, I'm joined by Doro Hinrichs and Kira Clark from Scott Logic and Peter Gostev, Head of AI at Moonpig. Together, we explore whether we can ever really trust and secure Generative AI – and what impact this will have on product and service design – before offering pragmatic advice on what organisations can do to navigate this terrain.
Cloud
The impending Digital Operational Resilience Act (DORA) aims to strengthen the IT security of financial entities such as banks, insurance companies and investment firms across Europe. The Bank of England launched an equivalent 'Operational Resilience' regime in March 2022. In this blog post, I share Monzo's smart, modern resilience strategy and look at why traditional resilience strategies put organisations at significant risk.
Delivery
Are story points just a waste of time? In this post, I take a critical look at the common practice of story pointing tickets, examining their origins and how they are most commonly used. I argue that story points often cause more harm than good and that maybe you don't need them at all.
Artificial Intelligence
In this blog, I describe creating InferGPT, a personalized chatbot, using Python, FastAPI, and React without the use of LangChain. Our backend handles complex queries with a multi-agent system and Neo4j database, aiming to provide tailored responses.
Sustainability
The Cloud Carbon Footprint tool also provides support for carbon calculations from On-Premise sources. I investigate how it works and list some pros and cons with its usage, along with some contributions we are hoping to make.