When a Small Language Model Beat Our LLM in Production: Right-Sizing Your Models The team invested in a state-of-the-art large language model, reasoning that more capability would translate directly to better outcomes. The infrastructure was built to serve this model. The APIs were optimized for its specifications. Deployment happened. And then the metrics came back: […]
This week, something new–I’ve split out my introductory essay pulling on the threads of this week’s reading from the articles themselves. So you can read either, or both! In other news… Introducing Noops Long time Web Directions speaker and friend Mark Pesce and I have sorted something new, Noops. Part research, part advisory, part punk, […]
The past week’s reading (read my breakdown of nearly 2 dozen articles here)—from across Phoronix to Stripe, from Answer.AI to the fringe blogs that are like canaries in the industry coal mine—points toward a the ongoing reorientation of the entire software development lifecycle. It’s not that AI makes code faster to write. It’s that AI, […]
Your Agents Pass Every Benchmark—Then Memory Breaks Them in Production There's a pattern that's starting to repeat across organizations experimenting with AI agents. The benchmarks look phenomenal. In controlled testing environments, the agent answers questions correctly, completes tasks reliably, and behaves exactly as expected. Your evaluation metrics are solid. Leadership is impressed. Then you deploy […]
How Many Agents Are Too Many? The Hidden Cost of Multi-Agent Systems The multi-agent architecture has become the aspirational design pattern for ambitious AI systems. The logic is appealing: distribute reasoning across specialized agents, orchestrate their collaboration, and watch them tackle problems that single models struggle with. But somewhere between the whiteboard architecture and production […]
This week we have almost certainly the biggest roundup of articles ever in a Weekend Reading–going all the way back to about 2006. We also announced a significant number of speakers for AI Engineer across all tracks. This one is selling fast, so start planning now! And while it’s still a bit further off, at […]
This week I published a long article inspired by the structure of scientific revolutions, Thomas Kuhn’s groundbreaking work on history, philosophy, and sociology of science from the late 1950s and early 1960s. The resistance to AI-assisted software development among experienced software engineers isn’t random or capricious–it follows the pattern Thomas Kuhn identified in scientific revolutions […]
TL;DR: The resistance to AI-assisted software development among experienced software engineers isn’t random or capricious–it follows the pattern Thomas Kuhn identified in scientific revolutions sixty years ago. What we’re witnessing isn’t a tooling debate. It’s a paradigm shift, complete with anomaly denial, incommensurable worldviews, and paradigm defence mechanisms that have played out very similarly in every intellectual revolution Kuhn observed. Understanding this pattern won’t make the transition painless, but it might make it possible.
A couple of quick notes before this week’s huge crop of articles. We’ve just announced the first round of keynote speakers for the upcoming AI Engineer Conference. I’m incredibly excited and proud of the program we are bringing together.And speaking of programs, CFPs close tomorrow for AI Engineer and AI x Design. We’d love to hear your proposals! And tickets […]
We’re incredibly excited to announce the first round of speakers for AI Engineer Melbourne, coming June 3–4, 2026. It’s a lineup that will bring together engineers, researchers, and leaders who are shaping how we actually build with AI — from the models themselves to the teams and systems around them. In total we’ll have nearly […]
Hardware is ready for its moment Last week, in less than a day, I programmed an M5Stack Core2 to be my personal recording assistant. I’d been using my iPhone to capture voice memos, then manually transferring the audio to my Mac and going through a series of largely manual steps to turn recordings into transcripts and ultimately […]
This week I’ve published a piece that tries to bring together a lot of what I’ve been thinking about in terms of the clearly rapidly increasing capability of not just frontier language models but the software ecosystems around them, and some of the first-order impacts these might have in coming weeks and months. I See Dead […]
I. At the end of M. Night Shyamalan’s celebrated The Sixth Sense, Bruce Willis’s character — a child psychologist — learns something the audience has probably been slowly working out the entire movie: he is, in fact, dead. The film only really bears one watching, because once you know the ending, you realise the whole thing […]
Last week, I observed, in the words of Taylor Swift, that there is a lot going on right now. So it’s ironic that this week I only managed to amplify two posts of the many that I read on the web. But I did manage to post two longer articles, and I sat down with […]
When I hear criticism of or scepticism about AI code generation, in my conversation with often quite experienced software engineers, it often goes something like this: “I tried it and it didn’t work” or “the code quality was terrible.” Fair enough. But then I ask: when was that? Six months ago. A year ago. Sometimes […]
Web Directions South is the must-attend event of the year for anyone serious about web development
Phil Whitehouse General Manager, DT Sydney
