Episode 59: Patterns and Anti-Patterns For Building with AI

Vanishing Gradients

Content provided by Hugo Bowne-Anderson. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Hugo Bowne-Anderson or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://player.fm/legal.

16d ago 47:37

MP3•Episode home

John Berryman (Arcturus Labs; early GitHub Copilot engineer; co-author of Relevant Search and Prompt Engineering for LLMs) has spent years figuring out what makes AI applications actually work in production. In this episode, he shares the “seven deadly sins” of LLM development — and the practical fixes that keep projects from stalling.

From context management to retrieval debugging, John explains the patterns he’s seen succeed, the mistakes to avoid, and why it helps to think of an LLM as an “AI intern” rather than an all-knowing oracle.

We talk through:

Why chasing perfect accuracy is a dead end
How to use agents without losing control
Context engineering: fitting the right information in the window
Starting simple instead of over-orchestrating
Separating retrieval from generation in RAG
Splitting complex extractions into smaller checks
Knowing when frameworks help — and when they slow you down

A practical guide to avoiding the common traps of LLM development and building systems that actually hold up in production.

LINKS:

🎓 Learn more:

Hugo's course (this episode was a guest Q&A from the course): Building LLM Applications for Data Scientists and Software Engineers — https://maven.com/s/course/d56067f338

60 episodes

#Tech #Hugo BowneAnderson Its #Data Science #Machine Learning