David's Debbie App
Another little bespoke app I built for myself - this one translates English and German live so I can talk to my sister-in-law.
Artificial intelligence
View All
Climbing the Ladder of Abstraction
I gave a talk at AI Practitioner London on what 'good enough' looks like when you can no longer review every line an AI writes.
The Embedded AI Trio
Ethan Mollick on embedding AI builders alongside subject-matter experts - and why, as someone who has been doing this, I have mixed feelings about it.
Recent Post
LLM Evals Lesson 2 Error Analysis
Notes from lesson 2 of Hamel and Shreya's LLM evaluation course - covering error analysis, open and axial coding, and systematic approaches to understanding where AI systems fail.
Hamel & Shreya's LLM Evals Course: Lesson 1
Notes from the first lesson of Parlance Lab's Maven course on evaluating LLM applications - covering the Three Gulfs model and why eval is where most people get stuck.
Cogs / Interns / Human Tasks, a practical framework for AI transformation
Trying to blend together two AI Framework styling into one that's more practically useful
Synthesising a new framework for AI Transformation
I like bits of Brunig's and Mollick's AI frameworks, but neither quite works for me.
Error Analysis for Improving LLM Applications
A systematic approach to analysing and improving large language model applications through error analysis.
Why we need Experiment-based Roadmaps in the AI Product Era
Why evaluation-driven experimentation creates better roadmaps in AI products.