Kira Howe

Posts42 entries

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

February 26, 2025

Making data useful

How do we turn messy data into profit?

Making data useful is difficult. The whole point of data engineering/science/analysis/etc is to turn all of the endless piles of information we collect into something that people find valuable. I've spent the better part of the last decade in my career as a software engineer building systems that do this, and I've noticed that it is remarkably difficult to do well. There are many points where the process breaks down, and no silver bullet for fixing them. I've spent a lot of time trying to organize my thoughts on the topic and wrote this down one night: […3 min read]

post#data-engineering#data-science

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

December 31, 2024

OSS Updates November and December 2024

This is a summary of the open source work I spent my time on throughout November and December 2024. This was the last period of my ongoing funding from Clojurists together. It's been such a magical year in many ways and I'm so grateful to have had the opportunity to spend so much time focusing on open source this year. It was a fantastic experience and I hope to be able to take another professional hiatus at some point in the future to do it again. […7 min read]

post#clojure#clojurists-together#open-source#oss-updates

December 30, 2024

Yet another website reboot

Every year around this time I get an uncontrollable urge to redo my personal website. It's total madness but I don't know how to stop it. I am very inspired by other bloggers who are able to sustain a coherent presence on the internet for decades, and I want to be one of them. I always think I've narrowed down the problem and have a reasonable solution in mind, but really it's just the same cycle repeating itself. […2 min read]

post#blogging#static-websites

Overcoming perfectionism

The main thing I want to overcome in 2025 is perfectionism. I have a very hard time making progress on projects until I'm confident they'll be "good", but the problem is that this is a totally arbitrary descriptor and usually irrelevant anyway. Not wanting to do things unless they're perfect prevents me from doing so many things in the first place. It's very frustrating but I don't know how to fix it yet. This is something I plan to work on this year. […1 min read]

post#personal#reflections

October 31, 2024

August 31, 2024