This is the eighteen-month recap: the talk I gave on day two of AI Engineer Singapore. A lot has happened since the six-month recap in Melbourne. The recording is below, followed by an edited transcri...

This is a follow-up from my previous post about AI as an economic weapon. If you haven't read it, I suggest that you do before proceeding. AI as economic warfarePeople often ask me how I feel about o...

People often ask me how I feel about open-source models, and to be clear, I'm very supportive of them. But I can't help pondering about the following... Open source always was and always will be a fi...

This one is short and sweet. if you want to port a codebase from one language to another here’s the approach: 1. Run a ralph loop which compresses all tests into /specs/.md which looks similar to “s...

Hey folks, the last year I've been pondering about this and doing game theory around the discovery of Ralph, how good the models are getting and how that's going to intersect with society. What follow...

I'm going to make this a really quick one because this is doing the rounds, and whilst I've tweeted about it, it's time to dig in. Pragmatic Engineer's @GergelyOrosz is on a "secret email list" of ag...

YouTube video by Geoffrey Huntley

YouTube video by Geoffrey Huntley

YouTube video by Geoffrey Huntley

I was my own worst gatekeeper until I realised that engineering isn't about credentials, it's about how I approach building software.

It's a strange feeling knowing that you can create anything, and I'm starting to wonder if there's a seventh stage to the "people stages of AI adoption by software developers" whereby that seventh stage is essentially this scene in the matrix... It's where you deeply understand that 'you can now

I just finished up a phone call with a "stealth startup" that was pitching an idea that agents could generate code securely via an MCP server. Needless to say, the phone call did not go well. What fol...

It's a meme as accurate as time. The problem is that our digital infrastructure depends upon just some random guy in Nebraska. Open-source, by design, is not financially sustainable. Finding reliable...

😎The following was developed last month and has already been delivered at two conferences. If you would like for me to run a workshop similar to this at your employer, please get in contact. Hey ever...

This blog post intends to be a definitive guide to context engineering fundamentals from the perspective of an engineer who builds commercial coding assistants and harnesses for a living. Just two we...

It's a meme as accurate as time. The problem is that our digital infrastructure depends upon just some random guy in Nebraska. Open-source, by design, is not financially sustainable. Finding reliable...

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...

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...

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?...

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...

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...

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 ...

💀🔥 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

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...

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...

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

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

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 -

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 them. But when the context gets too complex or concerns within the context are mixed, they lose the thread and spiral into hilariously (or frustratingly) wrong territory. Let’s dive into why this happens and how to

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 tool call invocation starts to fail We are in another era of "640kb should be enough for anyone." LLM context windows like RAM in an IBM 8086 XT are a precious resource, but for some reason or another, engi

It’s an old joke in the DJ community about upcoming artists having a bad reputation for pushing the audio signal into the red. Red is bad because it results in the audio signal being clipped and the mix sounding muddy. It’s a good analogy that applies to software engineers in the future, however, as these LLMs have context windows. Claude 3.7’s advertised context window is 200k, but I've noticed that the quality of output clips is at the 147k-152k mark. Regardless of which agent is used, when

Why did I do this? I have no idea, honest, but it now exists. It has been over 10 years since I last had to use the Win32 API, and part of me was slightly curious about how the Win32 interop works with Rust. Anywhoooo, below you'll find the primitives that can be used to connect Microsoft Paint to Cursor or ClaudeDesktop and use them to draw in Microsoft Paint. Here's the source code. GitHub - ghuntley/mcp-server-microsoft-paintContribute to ghuntley/mcp-server-microsoft-paint development by c

This is a follow-up to Dear Student: Yes, AI is here, you’re screwed unless you take action...Two weeks ago a student anonymously emailed me asking for advice. This is the reply and if I was in your shoes this is what I’d do. So, I read your blog post “An oh f*** moment in time” alongside “The future belongs to idea guys that can just doGeoffrey HuntleyGeoffrey Huntley but targeted more towards parents. My son recently turned ten, and after school, we have been building (and authoring blog pos