Geoffrey Huntley

by now, most people should be aware that we're in a cost of compute crisis.

people are failing a curiosity test right now.

I have to say, Peter Steinberg (aka lobster man) is absolutely brilliant.

All right, I'm going to open up a history lesson because it's been a couple of generations of software engineers since this essay, and I have to assume not everyone knows what a cathedral is.

Josh Wulf has been running a show called Agentic Engineering, and he asked me on.

Justin Cormack, who worked on MirageOS and Unikernel Systems back in the day, has been noticing what I've been noticing: people are discovering (or rediscovering) unikernels again.

When Ralph was published last year, I sat on it.

Here's something I've been meaning to write up for a while.

I don't know if you've noticed yet, but JetBrains reported a net loss for the first time in its recorded history. https://www.helgilibrary.com/companies/jetbrains Before we go into this, let's rewind time to January 2025, nearly a year and a half ago, when

There are many things that are uncertain in our industry right now, but one thing I am certain about, and have been for almost 13 years, is that Nix is a terrible programming language.

It's kind of strange seeing all these discussions about software factories... and the like.

I sat down with the folks at AI21 Labs for their YAAP podcast at the AI:Engineer World Fair, and we went deep on something I've been chewing on for most of this year: almost every decision in computing for the last forty years was made with a human in the…

One of the original promises of a personal computer was that the computer would be personal.

This is the eighteen-month recap: the talk I gave on day two of AI Engineer Singapore.

🎉 It's been a busy six months, that's for sure.

Some personal hot takes from AI: Engineer Miami follows... 1.

This is a follow-up from my previous post about AI as an economic weapon.

People often ask me how I feel about open-source models, and to be clear, I'm very supportive of them.

This one is short and sweet. if you want to port a codebase from one language to another here’s the approach: Run a ralph loop which compresses all tests into /specs/.md which looks similar to “study every file in tests/* using separate subagents and docu…

Below you'll find an AI transcription of everything we riffed about.

Hey folks, I'm currently over in SF.

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.

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.

I am fortunate to be surrounded by folks who listen and the link below post will go down as a seminal reading for people interested in AI context engineering.

I’ve been thinking about how I build software is so very very different how I used to do it three years ago.

In woodworking, there's a saying that you should work with the grain, not against the grain and I've been thinking about how this concept may apply to large language models.

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...

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.