Also worth taking a look at is the mimo harness. It's a fork of opencode with some new modes added for long horizon tasks. One of the better open harnesses out there at the moment.
If you are spending time on all text forums like this, you are likely a person whose skill set skews towards the verbalization of abstract concepts. This is also the exact skill set needed to use LLMs well. If you are able to articulate exactly what you want in a concise prompt, little else is needed.
I think we tend to overlook the fact that LLMs have tilted the scales heavily in favor of those with good verbal skills. A huge portion of the population (including a portion of highly skilled software engineers) is not great at doing this. For them, harness skills still act as a kind of scaffolding; they support automated work on a project in cases where insufficient details is given in the prompt.
In my experience, while software engineers can be socially awkward/introverted, they generally do have good verbal skills, an excellent vocabulary and can be concise and articulate in writing, when there's no social pressure. There are some exceptions of course, but being able to translate an idea or set of tasks into a concise written language form is essentially what programming is.
The closest I get to finding skills useful is when I find myself repeating myself to an LLM. This tends to happen most when I am starting new projects and want to communicate basic design principles and patterns to follow and libraries to use. What I did was to factor and store these "chunks" of instruction in some text files. I then made a little script that can list what chunks are available and when given a subset will essentially `cat` the selected files to emit AGENTS.md content which I save into the new project or append to shore up an existing one.
Your observation on the readership bias of HN is a good one for people to add to their HUMANS.md before reading and commenting. :)
No, the fundamental problem is ios. There are a bunch of features that ios locks down so that you are essentially forced to use apps. Want to send push notifications? You need an app. Want to be able to wake your app up in the background to do stuff intermittently? You need an app. Want to get your app on the home screen? Once again, you need an app. And before anyone says you can do this with PWAs, yes, that's true. But the steps required from your users in order to get a PWA running on ios are so cumbersome (by design) that nobody even bothers. And since ios has something like 60% of market share in the US, we're stuck with apps.
You forgot to mention the part where, to use any of the PWA features, you now have to get the user to close safari, and re-open the page via the icon now on the homescreen. Not exactly easy UI.
If that's a concern, an easy alternative is using companies like novita or fireworks.ai to run open source chinese models. They are incredibly price competitive, have strict data retention policies, and in general are quite fast. Also, you don't get used to a model and suddenly get rug pulled when the provider decide to upgrade.
I mean, that works for you since you're retiring. But for people still working in the industry, you adapt or die. As it's always been.
The fact of the matter is, a person working with a bunch of agents is a lot more productive than just a person. It makes research faster. It makes experimentation faster. It makes output cleaner. And this is true across many disciplines, not just tech.
Also, it is a skill. Yes, anyone can chat with an LLM. But understanding the optimal work flow for what to delegate and what to do yourself is difficult. Understanding the need for precision in the language used, and learning how to elegantly phrase things that were previously just abstract thoughts is absolutely a talent that can be refined.
If i had to guess, I'd say we'll probably see major breakthroughs across multiple disciplines within the next decade, largely because researchers and engineers can cover much more ground individually now, freed from the slow moving coordination mechanisms that team dynamics require. Pretty good for "spicy autocomplete" as you put it.
> I mean, that works for you since you're retiring. But for people still working in the industry, you adapt or die. As it's always been.
There are jobs outside of IT. They are harder, they have less benefits, they pay less. It's a whole project to switch your lifestyle so you can even afford them.
I know nobody who regrets making the jump. I hope to make it within this year. I'll be poor, but at least I won't work in IT.
> But understanding the optimal work flow for what to delegate and what to do yourself is difficult.
No it's not, you can learn it in less than a day. I've done it a few times while evaluating how much the agents have progressed (despite what people keep saying, not much).
> Understanding the need for precision in the language used, and learning how to elegantly phrase things that were previously just abstract thoughts is absolutely a talent that can be refined.
Some of us learned technical writing to communicate with _humans_ before, and we're sitting here alternating crying and laughing as y'all scramble to figure it out just to put all that into a hallucination machine.
Respect. I moved countries for lower cost of living, and I’m gonna become a starving artist, so to speak, trying to use my software skills to make myself useful and earn enough to buy food, in a field where human ingenuity still reign supreme.
And if I ever find money under the mattress, I’ll make a solar farm. Something useful for the world, for once.
Better content and poor than living in golden handcuffs.
If your worry is that you won’t be able to “keep up” and you’ll be laid off, or fired, just wait for that to happen. Keep making a paycheck until then. Then you can start your barista job.
If the problem is that you hate the work, then fine. But why barista? Fine, if that’s what makes you happy. But there are a million jobs out there _if you are willing to relocate_.
Bluntly? Because working with y'all is becoming insufferable. Because I don't want to work in IT. Note this isn't "I don't want to program" or whatever. That's cool and fun. But the people in here? Oh gods.
Also I'm sick and tired of working on projects where the best social benefit from my work would be if I stopped. And IT has this talent of doing this to even most superficially useful projects. I worked on solar panel software that got turned into a scam by marketing. That takes a talent, of sort.
The best time to jump out of IT was to never get into it. The second best time is now.
As for why barista? People need food and drink and coffee is great.
It depends on where you land. Not all programmers (and their managers) are brain-amputated zombies. But I do admit that finding that rare pocket of sanity requires a good portion of luck.
Are they? I remember when heavyweight IDEs where all the rage, there was a similar sentiment that if you weren't using one of them then you would eventually be so much slower that you'd be out of a job. It only took maybe five years until people started asking themselves if the dependency on a big IDE (and cost) was worth it. I don't think anyone would look at someone who prefers a stripped down text editor today and think they are backward or doing it wrong.
We have yet to see hard numbers on time saved by those who use LLM tooling extensively. It could be it doesn't turn out as compelling as we might expect.
Just sayin', I never forced software developers to use NetBeans or Intellij IDEA. I'm certainly not changing my tune and forcing them to use LLM tooling either.
Maybe it depends. If what you want to build is one-shot crap anyway, then micromanaging LLMs to make them vomit what you need for that is "productive". I wouldn't know, because I prefer real work over the make-believe and leave the AI coding acolytes to be left behind and die when their ingenious plans explode in their faces.
Vim and Emacs can do a lot of what IDEs used to offer thanks to language servers and build servers. Before those (lang/build servers) they were largely useless for large scale development (believe me, i tried).
It can put out code much faster than any software dev. And if you are careful with your prompts and demands, it is good quality code as well.
Especially for visualising data, to just get a quick look at, it can now be done in lightning speed and I am quite familiar with "manual data processing" in a few languages.
AI use me decently outcompetes manual me. Sometimes there are also stupid tasks. Data must be serialised in a certain way for some stupid reason. You prepare the info to be digested and the busywork can be done by agents with little oversight, which otherwise would have taken you a few hours. There simply is a limit in how fast you can read, look up field names, etc... If you outsource these critical paths to AI, you can gain productivity.
I also start way more side projects now and I like manual coding a lot.
Of course, it isn't the quantity. It is more about the features you wouldn't implement because manual dev takes a long time and why not let the AI spin up a non-critical site for administration or testing just for you. The cost/benefit calculation shifts a bit.
That said, if you get something quite heavy to lift off, it probably is a decent engineering feet. Not saying it would be the best plane :)
> a person working with a bunch of agents is a lot more productive than just a person
[citation needed]
I try LLMs for something every couple of months, and I have yet to see them produce anything actually correct. Calling non-existing library methods, confabulations, etc.
But sure, they produce a lot of stuff in a short while. The utility of any of that another question.
> I try LLMs for something every couple of months, and I have yet to see them produce anything actually correct. Calling non-existing library methods, confabulations, etc.
That's too pessimistic, the productivity gains are real and substantial.
OTOH, the hype train is out of control. It is nowhere near perfect and requires a lot of handholding and guardrails to avoid going sideways.
You need to adopt it to stay relevant, but don't fall for the excessive hype. At the end of the day the limitations are significant.
I ask in honesty, have you used LLMs? Seems to me the productivity gains are obvious.
As for my source, it is my experience at work for both myself, and my direct reports, and my peer teams.
Tiny example: a certain recurring task we need to do to help other teams which requires somewhat tedious analysis but rarely a lot of high level thinking, plus a bit of decision making. A year ago I'd do maybe 2-3 per day because each one took about 30 minutes so I had to find slices of uninterrupted time between other work to complete them.
Just tonight as I was wrapping up the day I did 19 of these in an hour while also catching up on email. I let the bots do all the research in parallel, as each one completed the research I'd either tell it "ok, do it", or if it was asking me for a decision I'd decide and tell it how to proceed.
I count myself as an AI skeptic, in the sense that the hype is way above reality. But that doesn't mean there isn't a huge amount of real gains.
I use these a lot. My favorite use case is templates, especially ones that were not initially planned in the architecture.
Let's say i have some entity like an "organization" that has data that spans several different tables. I want to use that organization as a "parent" in such a way where i can clone them to create new "child" organizations structured the same way they are. I also want to periodically be able to pull changes from the parent organization down into the child organization.
If the primary keys for all tables involved are UUIDs, I can accomplish this very easily by mapping all IDs in the relevant tables `id => uuid5(id, childOrgId)`. This can be done to all join tables, foreign keys, etc. The end result is a perfect "child" clone of the organization with all data relations still in place. This data can be refreshed from the parent organization any time simply by repeating the process.
While not on the same level as these guys, I've done some similar stuff using Claude. This is a classic synergy example, where the output of human + LLM is far greater than just the human or just the LLM working on a problem. My experience has been that the LLM lacks fine grained judgement when it comes to allocating resources, or choosing a direction to work in. But once a direction is pointed out, it can do a deep exploration of that possibility space. Left alone, it would probably just go off on a tangent. But with someone holding the leash and pointing out areas to explore, it is a very useful partner.
i've been thinking about why we call them agent harnesses
i know all analogies suck in different ways but here goes:
coding agents are like horses. without a harness and bridle they'll the horse will do as it pleases -- a human can't travel very far and fast by foot but put a bridle and a harness on a horse, give it a bit of coaxing with carrot and stick, add in a bit a pointing the thing in the right direction and bingo you're off to the races!
So nobody will ever start another successful software project? People will, what, just stop creating software? I understand people's apprehension because of the pace of change, but this is just silly.
You're overstating the case, but I think there's a strong possibility people will prompt AIs to produce bespoke apps that solve their niche use-case rather than paying a developer to do it.
I pay for a SaaS app that tracks my finances, but it's not that great and missing some features I would like. Very soon I expect I'll be able to get a better, local-first replacement tailored to my needs by prompting Claude & Friends.
There are two big advantages to using a 3rd party system.
1) There are a lot of cases where aggregated user data, even if anonymized, allows for insights that you can't get using just your own data.
2) The software is really just a stand in for a process. A way of doing something, like record keeping or tax filing, etc. A lot of times it makes sense to follow an already established process rather than creating your own. You are less likely to encounter unexpected pitfalls that way.
I don't see how you can overcome those just by having an AI that can build simple crud apps at will.
I’m publishing a very simple app with very little human written code and so far 90% of the actual work has had nothing to do with development. Most of it has been the “business” stuff, especially since the app stores have a lot of compliance and setup requirements.
Your example of a financial app is perfect: maybe one day grandma will be able to vibecode a budget app but then how is she going to set up the integration with banks? Publish it to the App Store? Keep it updated with bug fixes and resolve security issues? Is the AI going to handle security and incident response too?
Maybe you’ll say that one day the AI will just handle all this automatically with zero input or setup, but I think we have to assume that we are still asking grandma to spend time writing down what she wants and interfacing with the AI a pretty substantial amount to get it finished.
The thing is, we are also talking about competing with a SaaS product that is already available for around $5/month, and the professional software developers working on that product also have access to AI (and a whole lot of other skills).
Even making grandma put in a few prompts here and there is going to result in enough wasted time to say “screw this, I’ll just pay $5 a month for Simplifi.”
I think developers overestimate the amount of people who want to create app. My friends are lawyers, doctors, musicians, Pr, sales and they really dont care about creating their own apps or software. They use their iPhones for calls and Instagram.
I can't even think of what #2 is. If the technology gets better at writing code perhaps it can start to do other things by way of writing software to do it, but then you effectively have AGI, so...
reply