People treat modern AI as either magic or a threat, and it’s neither. It’s a machine that has looked at an enormous amount of data and learned the patterns in it. This is a talk I gave at TechNExt 2026 on exactly that, starting with a single passenger list from the Titanic and building up to how a large language model guesses the next word.
All posts
AI
How does AI work under the hood?
A talk I gave on what’s actually happening inside modern AI. No magic, just patterns learned from data at a scale that’s hard to picture, from a single Titanic passenger list to large language models.
Eve Anderson
1 min read
Keep reading
Launch
The launch checklist for an AI-built app
Everything I check before an AI-built app meets real users: security, data protection, reliability, performance, scaling, deployment, code quality and accessibility, with the concrete points under each and how to prioritise them.
Eve Anderson
10 min read
Workflow
How to enable GitHub sync on your vibe-coded app (and why you should)
Connecting a Lovable or Bolt project to GitHub gives you a copy of the code you own, a full history you can roll back to, and the route onto real hosting later. Here is how to turn it on.
Eve Anderson
3 min read
Privacy
What GDPR actually asks of your AI-built app
A practical, engineer-not-lawyer walk through the GDPR basics an AI-built app needs to get right, and the two things to fix before you launch.
Eve Anderson
6 min read