Data fitter Kim

I see a new form of tech debt coming for dev teams - Comprehension debt. As more and more code is generated by LLMs, if teams don’t take the time to understand deeply what the generated code is doing, as well as code they write by hand… It’s only a matter of time before the code base starts looking unfamiliar to most of the team. It then becomes harder to discern if new code that LLMs generate is adding more spaghetti or if there’s a better approach. It’s a downward spiral from there - unrelated things break with every change despite existing tests passing, no one knows the full picture to be able to fix the root cause, not even an LLM, etc. So as tempting as it is to move super fast with LLMs, there’s only so much comprehension debt you can rack up before your code base silently becomes a Rube Goldberg machine under your nose.

Skeptical of this it's writing 100% of my code narrative. Trying to use the lowest credit plan for my coding agent now. Like only playing $10 at the races. Then occasionally hand write code as a pause

A quick app to explain dimensional modeling kimnewzealand.github.io/apps/dim-model…

Watching all the hot new ai tool debates... I think I am going to stay on the Augment course. I still believe it's a good product as coding with it is a low friction positive experience

So freaking tired of localhost battles on my local dev machine. Moving everything to sprites.dev Loving it so far.

I spent a day writing manual code. Actually not a bad way to slow down and do a stock take

Ran out of credits. Going to try changing models to manage my allowance better. #feellikeakidagain

I have been trying out different user testing sites eg maze useberry on our prototype. I couldn't find which let me recruit a user or 2 for free. Seems so obvious to try before you buy. Going to try AI to get feedback instead

llms: a bag of ifs agents: while loops subagents: functions task mgmt: for loops prompts: config files rag: ctrl+f memory: sticky notes

I saw recent release of docker sandboxes but Augment isn't supported yet

Still using Augment for my coding agent. Today I attached a screenshot of our MVP app Figma design and it coded up say 95% of the design without text prompt specifications. The main fixes were for gradient colours and spacing. Next step figure out sandbox options

The era of manual software development is coming to a close quickly. My view on software development has drastically changed. I believe in the future the role of engineers will be to build software factories, not the software itself. So far programmers have been manual factory workers now quickly being replaced by more efficient and better robots. Like it or not. That’s what’s already happening. Embrace change.

What are engineering interviews testing candidates for these days?

I consider myself a "just in time" developer. Like I have no idea how to work with sqlite databases in Python. At least not without an ORM. By the end of the day I will. Let me tell you the secret of how I do that... I read docs and play with code until it works. 🤫

Learn to ship. Shipping is a skill distinct from coding. Shipping is designing, coding, QAing, story-telling, teaching, marketing, selling, pivoting, iterating… It used to be that coding dominated in importance because of coding ability scarcity. AI will push you to go further.

I think one of the biggest misconceptions about these new AI tools is that they're easy to use - they're really hard to get great results out of but fantastic once you pick up all of the weird and completely undocumented tricks This recent piece is great open.substack.com/pub/mikecaulfi…

Learning more about the newer lake house interoperability of tools and formats by Zoe Steencamp #deb25.

Live app demo 🌟

Looking ahead to a Data 3.0 autonomous data stack by Zhamak Dehghani at @dataengbytes Sydney #deb25