The Interface: Building Blocks for Just-in-Time Software
The second of my 8 ideas to explore in 2026 in AI and technology. In this one I'm exploring just in time software, like lego blocks we pull together when we need them.
Topic
ai
A collection of 10 issues
Building LLMs.txt for the social sector
Another blog on the ins and outs of something I built, what it's all about, and why it might be a useful tool and/or concept. A llms.txt tool designed for specific use cases.
Building Open Recommendations
A full breakdown of how I built Open Recommendations, the inner workings, the choices I made, including provider agnostic AI, strict data structures, deciding whats a recommendation and whats just an observation, RAG, and weighting community feedback.
Is the best way to actually make AI work in an organisation to focus on constraints?
Pondering on how we actually need to focus on constraints when everything and anything is possible
Predictions for 2026 (or: What I'm Actually Thinking About)
The Predictions for 2026 that no-one asked for. Some of them are real, some are more just hope, most of them are firmly tongue in cheek.
Also I set out 8 ideas I'm thinking about when it comes to tech and AI infrastructure.
Which LLM? And how do YOU decide?
Thinking out loud on assessing which LLM models to use. Starting to build a framework based on real life applications
People as Code 2 - Collapse, rewild, regenerate.
People as Code reflects on how generative AI, built from human data, now mirrors and shapes us. As AI flattens difference and optimises for plausibility over truth, culture risks collapse.
Weeknote 22
A catch up on my summer and getting back to work. A bumper bunch of interesting things.
AI for better?
Are we in the FastAI era? A discussion on how I use AI and some of the things I consider when I do.
Why AI*?
* this should be read as if you are from the North East of England