AI budgets hit faster than expected. Token costs compound quietly in the background — until you’re mid-sprint and suddenly hitting limits. This video walks through 11 practical techniques developers can use to reduce AI costs without reducing what AI does for them. What’s covered: Every token saved is a token you can spend on harder […]
11 Tips to Reduce AI Costs in Software Development Read More »
Most developers handle GenAI’s non-determinism in one of two ways: they ignore it, or they try to force it away. Both approaches fail. There’s a better model. Topics covered: The quadrant doesn’t have a name yet – share your suggestions.
The Missing Mental Model for AI-Assisted Development Read More »
AI tools are generating 110% more code. Lead times are up 480%. Code churn is up 861%. Something is very wrong. This is a commentary on the Faros AI Engineering Report 2026 (“The Acceleration Whiplash”), surfaced by Kent Beck’s LinkedIn post. The data covers 22,000 developers across 4,000 teams. Kent Beck’s post: https://www.linkedin.com/posts/kentbeck_the-ai-engineering-report-2026-the-ai-acceleration-share-7471011014738841600-JErm/Faros report: https://www.faros.ai/blog/ai-acceleration-whiplash-takeaways
More AI Code, Less Production-Ready Read More »
Most developers using AI are optimizing for the wrong thing. Speed metrics and line counts are not quality — and AI makes that confusion worse, not better. This video is a reaction to Nolan Lawson’s article “Using AI to write better code more slowly,” published May 2026: https://nolanlawson.com/2026/05/25/using-ai-to-write-better-code-more-slowly/ Topics covered: Going slow with AI isn’t
Go Slow to Go Fast with AI: Writing Better Code, Not More Code Read More »
Most developers use AI assistants the same way they use a search engine: ask, get an answer, move on. That habit is costing them the most valuable thing AI can actually do. The real power isn’t in generation — it’s in conversations that build understanding before you write a single line of code. Topics covered:
5 AI Conversation Patterns Every Developer Should Know Read More »
Storing time series data in PostgreSQL or another relational database feels obvious – until the table hits 50 million rows and your queries take 15 seconds. The problem isn’t your schema or your indexes. You’re using the wrong tool. Time series databases are built especially for this usage pattern. We cover: If you’re manually partitioning
Fix Your Slow Time Based Queries Read More »
Code is a communication medium for two radically different audiences — the machine and the developer. In the age of LLMs, the machine-facing part is being commoditized. What remains?This video is a live commentary on Unmesh Joshi’s article “What Is Code?” published on Martin Fowler’s blog. Topics covered:
Reframing Code for the Age of LLM Assistants Read More »
AI coding assistants misunderstand your architecture — not because they’re buggy, but because architectural intent was never visible in the code to begin with.In this video I read through and comment on Ian Bull’s article “Sinks, Not Pipes: Software Architecture in the Age of AI”, adding my own perspective from my work on usable software
Why AI Coding Assistants Misunderstand Your Architecture Read More »
Most developers are leaving a lot on the table with AI coding assistants — not because the tools aren’t good, but because of a few fixable mistakes I keep seeing in real teams.In this video I cover three common mistakes and how to avoid them: Plus a bonus fourth mistake: only using AI for code
3 AI Coding Assistant Mistakes I See in Real Teams — And What to Do Instead Read More »
Are LLMs a higher level of abstraction in software development?
Are LLMs a higher level of abstraction? Read More »
