There is an interesting “new” problem in software development these days, and I suspect it’s keeping many a dev manager up at night. That problem is the tension between many devs and this new upending technology of LLMs. I’ve written a lot about the individual’s resistance to this new paradigm, but I’d like to talk through strategies of how companies should be handling it, and how I may be able to help out if that’s you. ...
A blog post by Geoff Huntley last year really lit a ‘fire’ under me, or at least showed me that one other developer out there was thinking about this new paradigm in the same way I was. This post discusses how some developers who are resistant to the new paradigm simply, “won’t make it”. We will see this bifurcation of software developers into the “accepting” vs the “resistant”. I honestly can’t tell you what I think will happen to the resistance long term, but I suspect they will either get on board the roaring train of capitalism with a new technology, or they will be left at the station. ...
I’ve been all over the place lately, coming up with ideas, trying them out, throwing away more code than I actually kept, etc. And this whole firehose of thoughts has uncovered another issue. We’re in this weird transitional phase where the old deterministic way of doing things and the new “ask an LLM to figure it out” way are both valid approaches to the same problem. And figuring out when to use which one is its own challenge. ...
In using the tools I’m limited with at my day job (github copilot, yuck), I’ve had to find some workarounds to the built in difficulties. Microsoft is doing a lot in that tool to really limit its costs, which, sure. But it does make this tool much less powerful than the unfettered tools and models (and I’ll point out, every time a developer has a bad experience with Agentic AI tools, you risk losing a customer for life). They are doing things like artificially limiting the context windows down to 100k tokens, adding stuff to the system prompt to make sure it doesn’t run for too long, etc. They’re obviously also using the “dumber” models and just calling them by their standard name, for instance there is no way in hell that the GPT-5 model in GHC is anything but the medium version or worse, because that thing compared to what I use on my own time is significantly nerfed. ...
One aspect of this new paradigm I’ve been really enjoying lately is rethinking all of these things we’ve just taken for granted for years. Like the fact that all of our tools are designed for humans. This usually will result in inefficiencies, such as wasted tokens going back to the model, or giving it more to sift through. But overall, I think we can do better than rg for search or curl to read a website. This led me to start building some new tools, to try this out. ...
It’s not all doom and gloom. In fact, I’m pretty excited about this change. It comes off weird sometimes because I, and most developers, I think, have a lot of thoughts about this new world. It’s a lot to process. I’ve spent the last, I dunno, four months chewing on what this means for my career, the industry, everything. Eventually I decided to start writing about it, and that’s how we got here. ...
I built something that still feels a bit surreal to watch in action: an orchestrator that chains together AI agents to handle the entire software development lifecycle. From planning to deployment, it’s agents all the way down. Honestly, it’s not even anything too impressive or hard to build at all. Just some simple python to handle a workflow system, and to wrap either the claude cli tool or codex cli. The really crazy part is that once you have the idea, it takes an afternoon to get it up and running. ...