Geoffrey Huntley

Scales yes, toys on the small are fun. If you find something on the small that can be automated without humans that can scale you are onto something.

Ya indeed, in theory one could black box anything TDD style with enough traces…

this should not be possible It might surprise some folks, but I'm incredibly cynical when it comes to AI and what is possible; yet I keep an open mind. That said, two weeks ago, when I was in SFO, I discovered another thing that...

ghuntley.com/no

Nothing

me too, me too :)

This is gold.

I'm super curious what incident led to the inclusion of "DO NOT discuss ANY details about how ANY companies implement their products or services on AWS or other cloud services" in the system prompt.

source code analysis of Amazon Kiro It's another day, and another coding tool has been brought to market that uses ripgrep under the hood. This time it's Kiro by Amazon. What follows below is an analysis of this coding agent: Study the...

ghuntley.com/amazon-kiro-...

the six-month recap: closing talk on AI at Web Directions, Melbourne, June 2025 Welcome back to our final session at WebDirections. We're definitely on the glide path—though I'm not sure if we're smoothly landing, about to hit turbulence, or perhaps facing a go-around. We'll see ...

check out the bigger one btw :P ghuntley.com/six-month-re...

Cheers mate.

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?...

Good post by @ghuntley.com onbusing AI for coding ghuntley.com/play/

Ralph Wiggum as a "software engineer" If you've seen my socials lately, you might have seen me talking about Ralph and wondering what Ralph is. Ralph is a technique. In its purest form, Ralph is a Bash loop. while :; do cat PROMPT.md | n...

ghuntley.com/ralph

Claude Sonnet is a small-brained mechanical squirrel of <T>

ghuntley.com/cars/

AI coding tools are perhaps our new terminal emulators So I'm currently over in San Francisco. I've been here for almost two weeks now. I'll be heading home to my family in a couple of days. But over the weekend, I had the opportunity to drop into the Com...

ghuntley.com/vt100/

the six-month recap: closing talk on AI at Web Directions, Melbourne, June 2025 Welcome back to our final session at WebDirections. We're definitely on the glide path—though I'm not sure if we're smoothly landing, about to hit turbulence, or perhaps facing a go-around. We'll see ...

ghuntley.com/six-month-re...

Whenever Gergly wants to catchup again I guess :)

gm

Dropping the truth on AI tooling relating to software development at the moment - @ghuntley.com

We need better tools for sure but this will be getting better.

Why do we even need an IDE?

I have been playing with this idea too ajfisher.me/2024/10/28/s...

#wdcode

Today I'm releasing a chrome extension called "piss off all designers in the world" which when activated changes all websites to always use comic sans.

cc @mandymichael.bsky.social

GitHub - ghuntley/piss-off-all-designers-in-the-world: 💀🔥 OBLITERATE THE TYPOGRAPHY ESTABLISHMENT 💀🔥 A Chrome extension that transforms any website into a beautiful Comic Sans masterpiece 💀🔥 OBLITERATE THE TYPOGRAPHY ESTABLISHMENT 💀🔥 A Chrome extension that transforms any website into a beautiful Comic Sans masterpiece - ghuntley/piss-off-all-designers-in-the-world

Alright, I made a thing yesterday in front of the audience at @webdirections.org. It isn't charming. It's terrible. But it was used as an example of "play" to learn what an LLM can and cannot do — deliberate, intentional practice.

github.com/ghuntley/pis...

the z80 technique reveals the source code for Atlassian's 'rovo' AI assistant Ever wondered what happens if you take the technique at "Can a LLM convert C, to ASM to specs and then to a working Z/80 Speccy tape? Yes." and run it against the Atasslian Command Line (ACLI) interfa...

ghuntley.com/atlassian-ro...

The full talk is today, closing out @webdirections.org with it. Thanks @mandymichael.bsky.social for cocktails and fonts slide surgery last night. I’ve made some aesthetic changes. :)

@shibcodes.bsky.social overalls!!

nope!

Thank you

Keen to hear more dude care to hear more

I dream of roombas - thousands of automated AI robots that autonomously maintain codebases Just yesterday morning, I was writing a conference talk on best practices for maintaining the LLM context window, which was quite detailed. It contained the then best practices from the two blog posts...

🗞️ I dream of Roombas - thousands of automated AI robots that autonomously maintain codebases

ghuntley.com/ktlo

LLMs are mirrors of operator skill This is a follow-up from my previous blog post: deliberate, intentional play. I didn't want to get into the distinction between skilled and unskilled work 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 does not mean they're skilled as a software engineer in 2025, now that AI is here. In my view, LLMs are essentially mirrors. They mirror the skill of the operator. how do identify skill One of the most

📰 LLMs are mirrors of operator skill

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 actually 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 sharing their experiences in a particular company, in that particular codebase? Or are they coming from the perspective that they've tried at home and it hasn't worked for them there? Now this distinction is really imp

📰 deliberate intentional practice

💕

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 AI can be framed. Perhaps, the change we are going through right now in the software development industry is has a lot of similarities to the year 1404 when another disruptive innovation -

📰 from Luddites to AI: the Overton Window of disruption