the six-month recap: closing talk on AI at Web Directions, Melbourne, June 2025
🚧
hello consumers of RSS, if you're reading this, then you're ahead of the curve. These are the slides from my upcoming talk, which will be delivered at Webdirections in a couple of hours. After the talk is available, this post will be updated with the transcription. For now it serves as a reference to attendees at the conference for links found in the presentation.
An “oh fuck” moment in time
Over the Christmas break, I’ve been critically looking at my own software development loop, learning a new programming language, and re-learning a language I haven’t used professionally in over seven years. It’s now 2025. Software assistants are now a core staple of my day-to-day life as a staff
Geoffrey Huntley
Multi Boxing LLMs
Been doing heaps of thinking about how software is made after https://ghuntley.com/oh-fuck and the current design/UX approach by vendors of software assistants. IDEs, since 1983, have been designed around an experience of a single plane of glass. Restricted by what an engineer can see on their
Geoffrey Huntley
What do I mean by some software devs are “ngmi”?
At “an oh fuck moment in time”, I closed off the post with the following quote. N period on from now, software engineers who haven’t adopted or started exploring software assistants, are frankly not gonna make it. Engineering organizations right now are split between employees who have had that “oh
Geoffrey Huntley
from Luddites to AI: the Overton Window of disruption
I’ve been thinking about Overton Windows lately, but not of the political variety. You see, the Overton window can be adapted to model disruptive innovation by framing the acceptance of novel technologies, business models, or ideas within a market or society. So I’ve been pondering about where, when and how
Geoffrey Huntley
How to Build an Agent
Building a fully functional, code-editing agent in less than 400 lines.
Revenge of the junior developer | Sourcegraph Blog
The latest installment from Steve Yegge on viiiiibe coding and what that means for developer jobs.
Steve Yegge
Agents for the Agent
Amp now has new subagents and they’re more powerful than ever. Is everything changing again?
LLMs are mirrors of operator skill
This is a follow-up from my previous blog post: “deliberate intentional practice”. I didn’t want to get into the distinction between skilled and unskilled because people take offence to it, but AI is a matter of skill. Someone can be highly experienced as a software engineer in 2024, but that
Geoffrey Huntley
deliberate intentional practice
Something I’ve been wondering about for a really long time is, essentially, why do people say AI doesn’t work for them? What do they mean when they say that? From which identity are they coming from? Are they coming from the perspective of an engineer with a job title and
Geoffrey Huntley
From Design doc to code: the Groundhog AI coding assistant (and new Cursor vibecoding meta)
Ello everyone, in the “Yes, Claude Code can decompile itself. Here’s the source code” blog post, I teased about a new meta when using Cursor. This post is a follow-up to the post below. You are using Cursor AI incorrectly...I’m hesitant to give this advice away for free,
Geoffrey Huntley
You are using Cursor AI incorrectly...
🗞️I recently shipped a follow-up blog post to this one; this post remains true. You’ll need to know this to be able to drive the N-factor of weeks of co-worker output in hours technique as detailed at https://ghuntley.com/specs I’m hesitant to give this advice away for free,
Geoffrey Huntley
Can a LLM convert C, to ASM to specs and then to a working Z/80 Speccy tape? Yes.
✨Daniel Joyce used the techniques described in this post to port ls to rust via an objdump. You can see the code here: https://github.com/DanielJoyce/ls-rs. Keen, to see more examples - get in contact if you ship something! Damien Guard nerd sniped me and other folks wanted
Geoffrey Huntley
autoregressive queens of failure
Have you ever had your AI coding assistant suggest something so off-base that you wonder if it’s trolling you? Welcome to the world of autoregressive failure. LLMs, the brains behind these assistants, are great at predicting the next word—or line of code—based on what’s been fed into
Geoffrey Huntley
I dream about AI subagents; they whisper to me while I’m asleep
In a previous post, I shared about “real context window” sizes and “advertised context window sizes” Claude 3.7’s advertised context window is 200k, but I’ve noticed that the quality of output clips at the 147k-152k mark. Regardless of which agent is used, when clipping occurs, tool call to
Geoffrey Huntley
