I'm working on a bunch of different projects trying out new stuff all the time for the past six months.
Every time I do something I add another layer of AI automation/enhancement to my personal dev setup with the goal of trying to see how much I can extend my own ability to produce while delivering high quality projects.
I definitely wouldn't say I'm 10x of what I could do before across the board but a solid 2-3x average.
In some respects like testing, it's perhaps 10x because having proper test coverage is essential to being able to let agentic AI run by itself in a git worktree without fearing that it will fuck everything up.
I do dream of a scenario where I could have a company that's equivalent to 100 or 1000 people with just a small team of close friends and trusted coworkers that are all using this kind of tooling.
I think the feeling of small companies is just better and more intimate and suits me more than expanding and growing by hiring.
That's not really new, the small teams in the 2000's with web frameworks like Rails were able to do as a team of 5 what needed a 50 people team in the 90's. Or even as a week-end solo project.
What happened it that it because the new norm, and the window were you could charge the work of 50 people for a team of 5 was short. Some teams cut the prices to gain marketshare and we were back to usual revenue per employee. At some point nobody thought of a CRUD app with a web UI as a big project.
It's probably what will happen here (if AI does gives the same productivity boost as langages with memory management and web frameworks): soon your company with a small team of friends will not be seen by anyone as equivalent to 100 or 1000 people, even if you can achieve the same thing of a company that size a few years earlier.
That's what Amazon is doing. They simply increase the output norm and promise mass layoffs again. MS promises too, I'm not sure about details, but likely they don't cut the projects. Which means use of some sort of copilot is expected now.
The question is what happens to developers. Will they quit the industry or move to smaller companies?
Instagram was 13 employees before they were purchased by Facebook. The secret is most employees in a 1000 person company don't need to be there or cover very niche cases that your company likely wouldn't have.
Don't fall for the lottery winner bias. Some companies just strike it rich, often for reasons entirely outside their control. That doesn't mean that copying their methods will lead to the same results.
And for enterprise sales, you need a salesforce and many multi-billion companies have an enterprise salesforce. And documentation writers, and support staff, in multiple geographies, and events/marketing teams to support customers, etc.
Except it's not. All the big cloud providers catering to enterprises, whether SaaS or AWS/Google/Azure, definitely have large sales forces whether or not they thought they needed them at first or not.
> The secret is most employees in a 1000 person company don't need to be there or cover very niche cases that your company likely wouldn't have.
That is massively wrong, and frankly an insulting worldview that a lot of people on HN seem to have.
The secret is that some companies - usually ones focused on a single highly scalable technology product, and that don't need a large sales team for whatever reason - those companies can be small.
The majority of companies are more technically complex, and often a 1,000 person company includes many, many people doing marketing, sales, integrations with clients, etc.
I have worked for many companies and the majority of them are not technically complex. They are drowning in tech debt from when they were in a high growth phase and many of the employees they have are due to needing to handle that debt but the product itself is technically very simple.
In many companies, tech, whether good or bad, is not the majority of the workforce, nor is it necessarily the "core competency" of the company, even if they are selling technical products! A much bigger deal is often their sales and marketing, their brand, etc.
> Every time I do something I add another layer of AI automation/enhancement to my personal dev setup with the goal of trying to see how much I can extend my own ability to produce while delivering high quality projects
- Extremely strict linting and formatting rules for every language you use in a project. Including JSON, YAML, SQL.
- Using AI code gen to make your own dev tools to automate tasks. Everything from "I need a make target to automate updating my staging and production config files when I make certain types of changes" or "make an ETL to clean up this dirty database" to "make a codegen tool to automatically generate library functions from the types I have defined" and "generate a polished CLI for this API for me"
- Using Tilt (tilt.dev) to automatically rebuild and live-reload software on a running Kubernetes cluster within seconds. Essentially, deploy-on-save.
- Much more expansive and robust integration test suites with output such that an AI agent can automatically run integration tests, read the errors and use them to iterate. And with some guidance it can write more tests based on a small set of examples. It's also been great at adding formatted messages to every test assertion to make failed tests easier to understand
- Using an editor where an AI agent has access to the language server, linter, etc. via diagnostics to automatically understand when it makes severe mistakes and fix them
A lot of this is traditional programming but sped up so that things that took hours a few years ago now take literally minutes.
I worry that once I've done all that I won't have time for my actual work. I also have to investigate all these new AI editors, and sign up for the API's and work out which is best, then I have to learn how to prompt properly.
I worry that messing with the AI is the equivalent of tweaking my colour schemes and choosing new fonts.
If you can build, test and run your project entirely from the command line you're never locked in. Every project I've worked on in the past decade has not enforced a choice of editor, and most have been portable to 2-3 OSes.
> I also have to investigate all these new AI editors, and sign up for the API's and work out which is best, then I have to learn how to prompt properly.
I found this didn't take me very long. Try things in order of how popular they seem and keep notes on what you do and don't like.
I personally settled on Zed (because I genuinely like the editor even with the AI bits turned off), Copilot (because Microsoft gave me a free subscription as an active OSS dev) and Claude Sonnet (seems to be a good balance). Other people I work with like Claude Code.
When I do projects in this realm, it requires significant discussion with the business to understand how reality is modeled in the database and data, and that info is required before any notion of "clean up" can be defined.
Yeah, you still do all of that domain research and requirements gathering and system design as your meatbag job. But now instead of writing the ETL code yourself by hand you can get 80-90% of the way there in a minute or two with AI assistance.
Claude recommended I use Tilt for setting up a new project at work.
I wasn’t sure if it was worth it…is it pretty easy to set up a debugger? Not only do I have to adopt it, but I have to get a small team to be OK with it.
Our target deploy environment is K8S if that makes a difference. Right now I’m using mise tasks to run everything
Honestly the same is true for human devs. As frustrating as strict linting can be for newer devs, it’s way less frustrating than having all the same issues pointed out in code review. That’s interesting because I’ve been finding that all sorts of stuff that’s good for AI is actually good for humans too, linting, fast easy to run tests, standardized code layouts, etc. Humans just have more ability to adapt to oddities at the moment, which leads to slack.
My rule of thumb is that if I get a nit, whitespace, or syntax preferences as a PR comment, that goes into the linter. Especially for systemic issues like e.g. not awaiting functions that return a promise, any kind of alphabetization, import styles, etc.
Yeah I find it pretty funny that so much of us (myself included) threw out strict documentation practices because “the code should be self documenting!”
Now I want as much of it as I can get.
For us it’s been auto-generating tests - we focus efforts on having the LLM write 1 test, manually verifying it. Then use this as context and tell the llm to extend to all space groups and crystal systems.
So we get code coverage without all the effort, it works well for well defined problems that can be verified with test.
At some point you'll lose that edge because you stop being able to differentiate yourself. If you can x10 with agents, others can too. AI will let you reach the "higher" low hanging fruits.
Hopefully it’s better for individual strings, but I’ve heard a few native speakers of other languages (who also can speak English) complaining about websites now serving up AI-translated versions of articles by default. They are better than Google Translate of old, but apparently still bad enough that they’d much rather just be served the English original…
I guess similar to my experience with the AI voice translation YouTube has, I’ve felt similar - I’d rather listen to the original voice but with translated subtitles than a fake voice.
> they’d much rather just be served the English original
Yes. And the sites that gives me a poorly translated text (which may or may not be translated by ai) with no means to switch to English is an immediate back-button.
Usually, and especially technical articles, poor/unreadable translations are identifiable within a few words. If the text seems like it could be interesting, I spend more time searching for the in-english button then I spent reading the text.
Exactly. I wouldn't use it for bulk translations. This was literally, 4 words.
What was useful, was that I could explain exactly what the context was, in both a technical and usability context, and it understood it enough to provide appropriate translations.
UPDATE: I went and verified it. The translation was absolutely perfect. Not sure what this means for translation services, but it certainly saved me several hundred dollars, and several days, just to add one label prompt to a free app.
Weblate has been doing that for any number of languages (up to 200 or however many it supports) for many years, using many different sources, including public translation memory reviewed by humans.
It can be plugged into your code forge and fully automated — you push the raw strings and get a PR with every new/modified string translated into every other language supported by your application.
I use its auto-translation feature to prepare quick and dirty translations into five languages, which lets you test right away and saves time for professional translators later — as they have told me.
If anyone is reading this, save yourself the time on AI bullshit and use Weblate — it's a FOSS project.
If someone reports a translation error, how do you verify and fix it? Especially those tricky ones that have no direct translation and require deep understanding of the language?
That's an issue, regardless of the source of translation.
For my bulk translations, I have used Babbelon[0] for years. They do a great job. I wouldn't dream of replacing them entirely with ChatGPT.
What I would use ChatGPT for, is when I need to do a very minor change (like adding a simple prompt label to an app). Maybe just a few words.
Doing that through the translation service is crazy. They have a minimum price, and it can take a day or three to get the results. Since I work quickly, and most of my apps are free (for users; they usually cost me, quite a bit), changes can be a problem. Translations are a major "concrete galosh"[1].
With ChatGPT, I can ask, not only for a direct translation, but can also explain the context, so the translation is relevant to the implementation. That's a lot of work for bulk, but quite feasible for small "spot jobs."
As far as responding to reports of issues, that isn't always "black and white." For instance, I live in the US, and Spanish is basically a second US language. But it isn't just "Spanish." We have a dozen different variants, and proponents of each, can get very passionate about it.
For Spanish, I have learned to just use Castilian Spanish, most times. No one (except Spaniards) are completely happy, but it prevents too much bellyaching.
In some instances (like highly local sites), choosing a specific dialect may be advisable.
You verify by having a lot of friends, all over, who are true native speakers of languages. They usually aren't up for doing the translations, but are willing to vet the ones you do implement.
Localization is a huge topic, and maybe I'll write about it, sometime.
Definitely agree small teams are the way to go. The bigger the company the more cognitive dissonance is imposed on the employees. I need to work where everyone is forced to engage with reality and those that don’t are fired.
The thing is the luck as usually on the side of bigger battalions. Smaller teams don't have the rich and width of bigger companies. All in all we need the full spectrum from single person startup to mega corporations.
Some people like working for big companies so this is fine. It’s a shame that outside of Silicon Valley there isn’t a high density of small software companies.
Every time I do something I add another layer of AI automation/enhancement to my personal dev setup with the goal of trying to see how much I can extend my own ability to produce while delivering high quality projects.
I definitely wouldn't say I'm 10x of what I could do before across the board but a solid 2-3x average.
In some respects like testing, it's perhaps 10x because having proper test coverage is essential to being able to let agentic AI run by itself in a git worktree without fearing that it will fuck everything up.
I do dream of a scenario where I could have a company that's equivalent to 100 or 1000 people with just a small team of close friends and trusted coworkers that are all using this kind of tooling.
I think the feeling of small companies is just better and more intimate and suits me more than expanding and growing by hiring.