Geoffrey Huntley

VScode might be open source (to a degree), but the levers of control are on a different location. See https://ghuntley.com/fracture/ for an excellent blog on it.

VSCodium is the open source VSCxxx editor. https://underjord.io/the-best-parts-of-visual-studio-code-are-propriet… https://ghuntley.com/fracture/

i 100% agree - the folks who are best at ai-first engineering, they spend 3 days designing the test harness and then kick off an agent unsupervised for 2+ days and come back to working software. not exactly valuable as guidance since programming languages are very easy to verify, but the https://ghuntley.com/ralph post is an example of whats possible on the very extreme end of the spectrum

Location: Sydney, Australia Remote: Yes (last 7 years; globally) Willing to relocate: No (max 1 week a month out of Australia as required) Technologies: https://ghuntley.com/ Résumé/CV: https://linkedin.com/in/geoffreyhuntley Email: [email protected] A principal software engineer who is known to write and do conference keynotes about AI. Skillset-wise - a weird mix of software engineering, infrastructure, engineering management, and marketing with a security background. My current focus is automating job functions with AI and teaching people how to do it. I'm currently conducting interview loops.

These people are weird. The blog post that inspired this has this weird iMessage screenshot, like a shitty investment grift facebook ad: https://ghuntley.com/ralph/ Apparently one of the lucky few who learned this special technique from Geoff just completed a $50k contract for $297. But that's not all! Geoff is generous to share the special secret prompt that unlocked this unbelievable success, if only we subscribe to his newsletter! "This free-for-life offer won't last forever!" I am sceptical.

I found this article [0] by the same author and linked in the post more personally valuable - great insights into expert-level use of Cursor. [0]https://ghuntley.com/stdlib/

VSCode futures doesn't look good, OSS wise. "Microsoft loves open source" is the joke of the century. https://ghuntley.com/fracture/

I found this article, 'VSCode is Designed to Fracture'[0], insightful for its look at the current Microsoft. Its thesis is that VSCode is meant to leverage open source and popularity to increase closed source vendor lock-in to Microsoft. It cites recent examples of VSCode extensions being closed source, so that while VSCode seems open, the critical portions are not. It's worth reading the full article. 0: https://ghuntley.com/fracture/

> No productivity studies of individual developers tackling tasks show a 10x speedup; results tend to be anywhere from +20% to minus 20%. The only study showing a -20% came back and said, "we now think it's +9% - +38%, but we can't prove rigorously because developers don't want to work without AI anymore": https://news.ycombinator.com/item?id=47142078 Even at the time of the original study, most other rigorous studies showed -5% (for legacy projects, obsolete languages) to 30% (more typical greenfield AND brownfield projects) way back in 2024. Today I hear numbers up to 60% from reports like DX. But this is exactly missing the point. Most of them are still doing things the old way, including the very process of writing code. Which brings me to this point: > There have been absolutely zero indicators that this is true. I could tell you my personal experience, or link various comments on HN, or point you to blogs like https://ghuntley.com/real/ (which also talks about the origanizational impedance mismatch for AI), but actual code would be a better data point. So there are some open-source projects worth looking at, but they are typically dismissed because they look so weird to us. Here's two mostly vibe-coded (as in, minimal code review, apparently) projects that people shredded for having weird code, but is already used by 10s of 1000s of people, up to 11 - 18K stars now. Look at the commit volume and patterns for O(300K) LoC in a couple of months, mostly from one guy…

The beauty of Emacs though is that it puts the user in full control. There is nothing in the world stopping anyone from modifying anything in Emacs (at least on the Elisp layer), hence packages like this. VS Code on the other hand is designed to fracture [1]. MS can and has given proprietary API access to their blessed tools, forcing others to go through their much less capable extension API, hence the plethora of vscode forks. Even if you had the most motivated, excited group of people wanting to work on the latest and greatest LLM interactions with VS code, they would most likely be forced to fork. On the other hand, it just takes one motivated Elisp dev to implement whatever they want and make any external package they want integrate with it. Also, I think the derision from the Emacs community may be a bit overblown. I'm constantly seeing AI/LLM related plugins appearing for Emacs and they tend to get decent traction (e.g. https://github.com/karthink/gptel). [1] https://ghuntley.com/fracture/

My workflow for that kind of thing goes something like this (I use Sonnet 3.7 Thinking in Cursor): 1. 1st prompt is me describing what I want to build, what I know I want and any requirements or restrictions I'm aware of. Based on these requirements, ask a series of questions to produce a complete specification document. 2. Workshop the specification back and forward until I feel it's complete enough. 3. Ask the agent to implement the specification we came up with. 4. Tell the agent to implement Cursor Rules based on the specifications to ensure consistent implementation details in future LLM sessions. I'd say it's pretty good 80% of the time. You definitely still need to understand the problem domain and be able to validate the work that's been produced but assuming you had some architectural guidelines you should be able to follow the code easily. The Cursor Rules step makes all the difference in my experience. I picked most of this workflow up from here: https://ghuntley.com/stdlib/ Edit: A very helpful rule is to tell Cursor to always checkout a new branch based on the latest HEAD of master/main for all of it's work.

>Also, why is he even doing this? You can find some of the author's motivations here: https://ghuntley.com/a-new-chapter/ I obviously can't speculate beyond what's in there about the author, but for me, living in a bog standard apartment and working remote to support kids isn't exactly blog-worthy content. I used to live in apartments, and most of the new construction in the US is very cookie-cutter and sometimes depressing. So, here's what mine would be: 1) a challenging hobby that's useful and more engaging in off-hours than more computer hobbies. Building a livable van certainly seems more interesting than living in an apartment to me. 2) changing scenery at a whim, given the time investment to find a place 3) a van that you can resell or give to your kids I'd still choose a detachable RV though since it's probably way more comfortable for the price. Sure, I lose out on some options to stay for the night, but that isn't an insurmountable challenge if you can plan and live in a van. Living full time in an RV might also not be blog-worthy though.

> VSCodium is not "designed" to be less functional, since it is a project maintained by developers who are unaffiliated with Microsoft. In today's (OSS) world, employment or affiliation doesn't matter much. Microsoft can propose what they want and get what they want from the project, at the end of the day. I don't think these independent maintainers have power to say "No" (if a VSCodium developer can chime in here, I'd love to be stand corrected), or they risk VSCodium to be forked to VSCodiumX, by developers who are friendlier to the megacorp which loves Linux. Yes, VSCodium is a node to Chromium. "-ium" has a ring akin to "-ish" in today's conjecture. Freemium - Free-ish but not. Chromium - Chrome-ish but not. VSCodium - VSCode-ish, but not. This might be curse in the naming, but it feels, looks and works like that, in practice. The blog post I linked (for further reference, it's [0]) quotes a tweet which supports what I'm saying, heck even the blog post does a much better job of detailing what I was trying to say here in my previous comments. To circle back, the problem with -ium projects are, they are effectively banned from participating in the main ecosystem which drives these projects forward, and to be in "The Ecosystem", you need to use the closed source versions with pervasive data collection and whatnot. Heck, even Google abuses Chromium with "Experiments and Proposals", which they use to politely yet forcefully push the web to the places they want. VSCodium…

I'm kind of obsessed with this space and have spent way too long setting up VS Code and RStudio IDEs on my homelab. One area I struggle with when thinking about building container-based development environments is the best way to avoid mixing in your IDE specific dependencies with your project dependencies. I think some of the commercial tools do this, but I haven't gotten in set up well in my homelab. I just came across two articles by a former GitPod employer who moved to Coder (these are the two main providers of open-source VS Code in the browser solutions). They're both really interesting. The first is on how effectively Microsoft has used VS Code to fracture the market place to their advantage by strategically open-sourcing parts of VS Code while keeping many of its best features proprietary (Pylance, the python language server is a good example of this). https://ghuntley.com/fracture/ The second article is about why he thinks Coder's strategy is more promising than GitPod's prompting him to go work for them. It's not as detailed, but it touches on some of the parts of container-based development environments that I've found overly limiting. https://ghuntley.com/integrate/

Also out-speeding them, and that was before high speed inference. Out-ralphing them, you might say! https://ghuntley.com/ralph/ AGI ≈ artificial stupidity × infinite persistence

You can use the Ralph Wiggum technique: https://ghuntley.com/ralph/

ghuntley’s article on building a standard library of Cursor rules in Feb 2025: https://ghuntley.com/stdlib/ Looks like it has since been paywalled. https://web.archive.org/web/20250211140426/https://ghuntley.com/stdlib…

Vs code is a weapon, designed to fracture. It being “good” is a weapon as well. https://ghuntley.com/fracture/

That's just a ralph loop: https://ghuntley.com/ralph/ I can do that now with claude code and a "while true" bash loop. Or with the built-in "/schedule" in claude code to set an agent to run say once every few minutes.

https://ghuntley.com/loop/ and https://github.com/anthropics/claude-code/blob/main/plugins/ralph-wigg…

Isn't that what Geoff did: https://ghuntley.com/cursed/ OK, it wasn't a Claude Skill, but it was done using Claude.

On one hand, folks are complaining that even basic tasks are impossible with LLMs. On the other hand we have cursed language [0] which was fully driven by AI and seems to be functional. Btw, how much did that cost? I feel like I've been hugely successful tools like Claude Code, aider, open code. Especially when I can define custom tools. "You" have to be a part of the loop, in some capacity. To provide guidance and/or direction. I'm puzzled by the fact that people are surprised by this. When I'm working with other entities (people) who are not artificially intelligent, the majority of the time is spent clarifying requirements and aligning on goals. Why would it be different with LLMs? 0: https://ghuntley.com/cursed/

There is already a term for it! It's called "Ralph coding": https://ghuntley.com/ralph/

> Unless you happen to live off-grid and get your own electricity for free I just had to laugh and link this other article by the author https://ghuntley.com/internet/ Im not sure if he has a solar array but I assume so?

https://ghuntley.com/stdlib/ applies to claude as well. AI won't magically know your codebase unless it is pretty vanilla - but then you teach it. If it makes a mistake, teach it by adding a rule. You have to confine the output space or else you quickly get whatever.

As far as their bottom line and market control while openwashing, sure. As far as improving the security of the ecosystem as a whole, no. See https://ghuntley.com/fracture/, for a criticism of this strategy

How about converting a rust library into Haskell? https://ghuntley.com/oh-fuck/ That's from 6 months ago and the tooling today is almost night and day in terms of improvements.

Microsoft couldn't have telegraphed their intentions more clearly if they tried, yet tons and tons of people and organizations fell for it (again!). VS Code source is under MIT, but the built product is under an EULA - and all Microsoft extensions are under an EULA that requires the use of the EULA build. As has been already posted multiple times here... https://ghuntley.com/fracture/

This was foreseen 3 years ago: https://ghuntley.com/fracture/

This would help, but you can also use a more aggressive approach to cursor rules: https://ghuntley.com/stdlib/ Using file pattern matching and automatic attachment makes it much, much more sticky in my experience.