> The part that makes this powerful is that the LLM is the ultimate UI/UX.
I strongly doubt that. That’s like saying conversation is the ultimate way to convey information. But almost every human process has been changed to forms and structured reports. But we have decided that simple tools does not sell as well and we are trying to make workflow as complex as possible. LLM are more the ultimate tools to make things inefficient.
People want to do stuff, and they want to get it done fast and in a pretty straightforward manner. They don’t want to follow complicated steps (especially with conditional) and they don’t want to relearn how to do it (because the vendor changes the interface).
So the only thing they want is a very simple interface (best if it’s a single button or a knob), and then for the expected result to happen. Whatever exists in the middle doesn’t matter as long as the job is done.
So an interface to the above may be a form with the start and end date, a location, and a plan button. Then all the activities are show where the user selects the one he wants and clicks a final Buy button. Then a confirmation message is displayed.
Anything other than that or that obscure what is happening (ads, network error, agents malfunctioning,…) is an hindrance and falls under the general “this product does not work”.
> Non-technical users expect a CEO's secretary from TV/movies: you do a vague request, the secretary does everything for you. LLMs cannot give you that by their own nature.
Most people are indifferent to computers. A computer to them is similar to the water pipeline or the electrical grid. It’s what makes some other stuff they want possible. And the interface they want to interact with should be as simple as possible and quite direct.
That is pretty much the 101 of UX. No deep interactions (a long list of steps), no DSL (even if visual), and no updates to the interfaces. That’s why people like their phone more than their desktops. Because the constraints have made the UX simpler, while current OS are trying to complicate things.
So Cowork/Codex would probably go where Siri is right now. Because they are not a simpler and consistent interface. They’ve only hidden all the controls behind one single point of entry. But the complexity still exists.
SDL is kinda the king of “I want graphic, but not enough to bring a whole toolkit, or suffer with opengl”. I have a small digital audio player (shangling m0) where the whole interface is built with SDL.
Also a lot of software should be small. The only reason they aren’t (especially web) is because the trend is to bring in frameworks instead of using libraries. I spend more times tweaking code than adding features. The time spent on coding is way smaller than the time spent discussing about those tweaks
It’s all vibes based, we are not trying to be scientific here. /s
I discard most LLM advice and skills because either a script is better (as the work is routine enough) or it could be expressed better with bullet points (generating tickets).
> The single most valuable shift I made was treating every feature as a thinking problem first and an implementation problem second
That’s pretty much the whole point of software engineering. Coding is easy, solving problems is hard and can be messy (communication errors and workarounds to some inevitable issue).
If you’re familiar with the codebase, when you have a change request, you will probably get an insight on how to implement it. The hard thing is not to code it, but to recalibrate all the tradeoffs so that you don’t mess with existing features. That’s why SWE principles exists. To make this hard thing easier to do.
I'm running OpenBSD as a daily driver and one of its nicer point is not the security angle, but how simple and hackable it is, while still fairly capable in terms of hardware support. Linux may be more convenient, but its subsystems are too complex and not prone to quick modifications.
> Linux may be more convenient, but its subsystems are too complex and not prone to quick modifications.
LFS/BLFS. Which BSD has that?
I don't disagree with you fully, mind you, but I think this is mostly because many more noobs use Linux, whereas on the BSDs more people with a lot of knowledge use it. But even then I would reason that there are more experts using Linux than OpenBSD, simply due to numbers alone. Not all of them can be bothered to write blogs either. (And sometimes they have reallife hardships suddenly, such as Fefe.)
There is a reason the top 500 supercomputers all run Linux. No BSDs there.
They can’t have it. The BSDs are a complete system, where the kernel and utilities are built in sync. And building them is quite easy.
Linux complexity may give you flexibility, but most users systems are fairly simple. OpenBSD has a lot of documentation, and if that’s not sufficient, you browse the source code to see what’s happening.
I strongly doubt that. That’s like saying conversation is the ultimate way to convey information. But almost every human process has been changed to forms and structured reports. But we have decided that simple tools does not sell as well and we are trying to make workflow as complex as possible. LLM are more the ultimate tools to make things inefficient.
reply