Thank you, this is what I've been seeing. Structs and objects are easy, but the hard part is encoding the domain most accurately into given data types of the computer (or creating new data structures to solve the problem!)
If anything, I do expect the casual non-tech users to be making the most adaptable software because they have what they want in their head.
Although, part of what the dev does is figuring out the weeds, and only a part of users have the patience to sit through detail corrections. And the AI user has to verbalize their wants exactly too.
> I do expect the casual non-tech users to be making the most adaptable software because they have what they want in their head.
Those are the people who are most likely to give a monolithic prompt and then spend a week telling the machine 'I don't care about encryption or file permissions, just make it work.' Not to mention that most people can barely verbalize the problems they have with devices they use for 8hrs a day, let alone form a full, self consistant, project idea and then put it in writing.
if they're persistent and patient enough to see the result of what they think they want and iterate enough times they'll eventually learn. non-coders aren't dumb by default after all and I suspect they'll learn much faster than us because they won't be bogged down by the minutiae like reading docs.
Imagine you could build a piece of furniture without actually needing to know how to cut wood, drive nails etc. Imagine you could do it in 3d without knowing how to actually handle wood, you just have an image you can iterate on without actually costing you anything but time.
I remember the first big app I wrote in high-school. I had to learn C++, learn Qt etc. I knew what I wanted but putting that into code when I didn't know any of the libraries / tools was a huge time investment. If I had LLMs I could've done the same thing it took me 6+ months in probably less than a month.
> non-coders aren't dumb by default after all and I suspect they'll learn much faster than us because they won't be bogged down by the minutiae like reading docs.
They may have a perfectly good shot at being smart, but I still don't buy the argument. The reason they struggle to become coders (assuming they tried at all), in my experience, is a lack of problem-solving and debugging skills. There is no real shortcut here. An "image" of the chair isn't enough; when the first iteration is wrong, you have to be able to explain why it's wrong.
I think there are a lot of people out there with good problem-solving skills but for whatever reason did not get into programming or they tried and they got put off with learning the languages / libraries or got stuck and didn't find a solution easily enough and gave up etc.
With a sufficiently good LLM these people will skip the tedious part of programming that most of us had the motivation / patience to go through. All the folks saying that actually writing code wasn't the bottleneck have had a LOT of years to get to that point, years a lot of people aren't interested in going through.
I'm not saying lay people will be able to join mega projects and work at FAANG. I'm saying a sufficiently courageous lay person will be able to make an app to automate whatever tedious birocratic process their niche work hasn't seen a product yet.
I can absolutely believe this, actually. Considering how the access to rapid prototyping has rejuvenated my interest in programming when I am a seasoned programmer, I definitely see the value in that kind of jump-start.
And yeah, without LLMs, writing code absolutely can be the bottleneck sometimes, if only for psychological reasons. I've definitely experienced something like "coder's block" before. An anti-flow state, if you will.
(But skydhash is also right. The "unknown unknowns" are a big deal and there's only so much an LLM can do about that, at least unless the user is actively aware of the general shape of that problem and trying to learn via the LLM and fill in those knowledge gaps.)
> All the folks saying that actually writing code wasn't the bottleneck have had a LOT of years to get to that point, years a lot of people aren't interested in going through.
The years was not spent on learning how to code. The years was spent on learning about what needed to be coded. And that would have spanned multiple domains. Even the most basic production level software have multiple concepts that need to be integrated. And for that, they need to be learned.
Using AI without the requisite knowledge is playing Russian roulette. It’s kinda wanting to log into a file, and not thinking about disk storage being finite, and rotating the log file gives you flexibility. That’s not related to coding, it’s just hard thinking about the problem and the constraints (or finding a good book or article).
> Using AI without the requisite knowledge is playing Russian roulette
Every few months that revolver has a few more empty chambers and even if it shoots them in the foot, it can bandage them quite nicely. Will a solo lay person with an agent build a high quality high reliability software business? Doubtful. Will they be able to make a tool that helps them and 10 other people or a personal website? probably.
> Will a solo lay person with an agent build a high quality high reliability software business? Doubtful. Will they be able to make a tool that helps them and 10 other people or a personal website? probably.
Just take a quick look around to see how many daily tools and utilities are actually built by experts and industries. Yes, you can put a plank on top of two concrete blocks to make a bench, but many people don’t and prefer to have good bench made, even when it’s quite easy to DIY one.
So I don’t foresee lots of people trying to make custom tools, more so to keep a subscription active.
just because you have an idea doesn't mean it will work. kids come up with ideas all the time in their drawings, but they disobey the laws of physics and are therefore not feasible in reality. sure, the model can guide them, but eventually they would have to pick up the necessary knowledge.
The necessary knowledge needed with LLMs goes from needing to know programming languages and libraries to having a high level view of what is possible which is far easier and less boring to get
> Although, part of what the dev does is figuring out the weeds, and only a part of users have the patience to sit through detail corrections. And the AI user has to verbalize their wants exactly too.
Even with basic pseudocode and very lenient logical rules, most people won’t bother to provide a a good definition of some process, as it’s quite unnatural to be that logical. Instead, it’s mostly just playing around. When you ask the one that is supposedly 10x-ing his productivity to explain his mental model of their own projects, it’s often a wishlist instead of a real understanding of what he has built.
In my opinion code works when it works so there is less reason to care about the weeds. When code is a communication of intent between people, or even just between a person and their future self, learning to encode that intent well into the code takes practice. There are entire fields people have developed over this, like domain-driven design or data-oriented programming, ensuring the data shows what it means semantically.
It is impossible to reconstruct the intent/spec from the code. More often than not the intent is not clear in the code, and one has to track down the original author to check their context and decision at the time.
As the saying goes, naming things well is a hard problem. It's kinda mystical in a way, where only by knowing an entity's true name will one understand it.
However if it's communicated between agents one may care even less.
I have a custom build of this font, use it everywhere now.
One thing is that the width by default is too compact and the extended is too wide for my taste. Upon searching I found somebody's build that has width 576. I don't know why that number, but I used it in my current builds and it turns out pretty much perfect for terminal use for me, just wide enough.
The hookiest tail for lowercase l man, love it.
Even for my own website, with some tighter tracking and it can work okay as a text font.
Re: Width -- Same, default is too narrow and extended is too wide for my taste. The custom build has a default "semi-extended" which is just right for me and has a width of 548. Again no clue why that number, but if Iosevka says that is right then it is :) I do see that when I switch between semi-extended and a "regular" font like Cascadia Code that they seem to be the exact same width.
Attention is the limit for consumers, agree. I do wish for more Games that stay their course and don't overstay their welcome with fetch/grind quests, although balancing that pacing within storylines, or maintaining engagement/overwhelm balance is pretty much in the game maker's art form.
Also retiring the concept of game hours per dollar spent.
The recently popped up clean room implementations of software, along with the video game decomp/recomps, make me believe this is the case. That would mean only those with significant legal representation/protection are safe (big corporations, institutions, govt and military). Protection comes from applying strong legal force through TOS and a favoring law environment. Also means the big players can strongarm taking ideas from individuals without recourse, which is already happening right now, just going to be even more onwards.
Protection of law in this way, I believe stops at the national borders (e.g the Chinese cleanrooming US software would be safe), so I do expect this clean room trend to be a war of attrition at the nation state levels.
Not even needing the AI to think that, US consumers of the electric grid are already subsidising the unpaid bill of data centers. Just need those who are in charge of infrastructure to prioritize the AI consumption over humans, and shifting the books to make humans pay more for resources.
I had a server-side app made for personal stuff, and pico.css drop-in is a pretty good baseline for an usable UI/page. Also visited some web hosts and their sites look perfectly serviceable with Bootstrap. I think it's a good way to railroad some of the more egregious things LLMs might do with regards to CSS.
Pretty funny that I came up with the exact same thing for run-on sentences and passive voice, no sentence fragments, no if, no contrast-ives (not X, it's Y). Everyone is fighting the same battle with their LLMs it seems
Side point regarding the hand the author draws on whiteboard: it looks off because the finger joint closer to the fingertip cannot bend as much as the joint closer to the knuckle. Some artist taught me this on a YouTube video. It does make me think about how to teach and explain these intuitions you have to really put to words what is different, what looks off etc. and more importantly how to fix them. Coding might be the same case, I think? Maybe LLMs can help here.
If anything, I do expect the casual non-tech users to be making the most adaptable software because they have what they want in their head. Although, part of what the dev does is figuring out the weeds, and only a part of users have the patience to sit through detail corrections. And the AI user has to verbalize their wants exactly too.
reply