August 8, 2026

Is it all just vapourware?

Maybe I’m just too cynical but it’s really starting to feel like more or less all of this new “AI”/agent software is vapourware. I’ve been trying to take this whole “agentic development” thing seriously and there is just so much friction in this ecosystem it’s absolutely insane. It’s very clear that all this stuff is built by engineers who a) have free access to unlimited tokens and b) have no systematic review or QA process for usability testing or dogfooding their products except on the most straightforward of happy paths. […3 min read]

post#agent-driven-development#agent-tools#ai#ai-agents#ai-hype#software-engineering#vapourware

August 2, 2026

Have the models come full circle?

It feels like the big LLMs have come full circle. At first they were too naive to implement meaningful features autonomously and took so much handholding to get anything done it was quite a pain babysitting them. Then they got good enough to do meaningful software engineering work and there was (I now recognize in hindsight) a sweet spot at some point early this year where they got meaningfully better and good enough to take non-trivial work off my hands without causing dramatically more work. But now they're far too eager and require constant babysitting again. […2 min read]

post#agent-driven-development#ai-agents#ai-hype#ai-safety#coding-agents#developer-workflow#llms#software-engineering

May 26, 2026

January 4, 2025

Software engineering is table stakes

I'm going through a course on data engineering on Coursera right now and it's been super interesting. I've been one of those software engineers who works with data for a while now, and while I feel like I have a solid grasp of software engineering, I often feel like I'm fumbling my way through the more data-processing heavy parts of my job. I get that feeling like there must be a better way, but I don't know what it is, so I just put something together based on my paradigm as a software developer, and it often ends up being a sub-optimal solution. […2 min read]

post#best-practices#data-engineering#software-engineering

March 10, 2021

February 10, 2021

January 30, 2021

How state makes software complex

What makes large codebases so hard to reason about, and so hard to extend? I really want to find out because I'm tired of losing my mind working on them. One paper I love called "Out of the Tar Pit", by Ben Moseley and Peter Marks, argues that state is the main source of complexity in large software systems. This article is an overview of a couple of the ideas from that paper, along with some discussion about how we might conceptually think about necessary state in software in order to improve its overall quality. […6 min read]

post#complexity#papers#software-engineering

January 19, 2021

Becoming a software developer

I get asked a lot for advice on becoming a software developer. I didn't study anything related to software in university, but now it's what I do for a living. I also spent about 3.5 years mentoring with Lighthouse Labs, a local web development bootcamp, and watched (and would like to believe at least in some cases, helped) hundreds of people of every age from wildly diverse backgrounds get jobs as software developers. […13 min read]

post#careers#software-engineering