Some have expressed the opinion in this forum that the future of software lies in programs that are created and adapted at runtime, using genAI. I don't know how far we are from that.
It’s already here the question is just to what extent?
Are google search results modifying your software at runtime?
Take or agent chat for example, the output text is a ui, agents can generate charts and even constrained ui elements.
Isn’t that created and adapted at run time?
If you mean like agents live modifying your code. I think that’s pretty much here as well. Can read the logs and send prs.
The only thing is how fast that loop will execute from days or hours to mins or seconds, and what validation gates it needs to pass.
My git repo is pretty much self modifying personal software at this point, that I interface through the ide chat window.
But I don’t think we will ever lose the intermediary deterministic language (code) between the llm and the execution engine.
It would be prohibitively expensive to run everything through models all the time.
But I am starting to think we need a more precise language than English when talking with LLMs. That can do both precision and ambiguity when you need either.
> Some have expressed the opinion in this forum that the future of software lies in programs that are created and adapted at runtime, using genAI.
Good luck with that. Users will flood you with complaints if a button moves 5px to the left after a design update. A program that is generated at runtime, with not just a variable UI but also UX and workflows, would get you death threats.
I think many software adjacent folks are super excited because they can now have the personalized toothbrush they keep asking people to make for them.
The problem is that outside of that most people want boring and regular interfaces so they can get in and solve the problem and get out - they don't want to "love" it or care if its "sexy" they want it to work and get out of the way.
LLMs transmogrifying your software at ever request assumes people are software architects and creators who love the computer interface, and that just doesn't describe the bulk of the population.
Most people using computers use the to consume things or utilize access to things, not for their own sake, and they certainly don't think "what if I just had code to do x..." unless x is make them a lot of money.
A program that is generated at runtime is fine (we have interpreted languages and often compile on demand) - the issue is with the non-deterministic nature of the output.
I think the core issue is that non-deterministic output is great for a chatbot experience where you want unpredictable randomness so it feels less like talking to the mirror - but when it comes to coding I think we're pretty fundamentally misaligned in sticking to that non-deterministic approach so firmly.
>In Slovenia, this has resulted in so-called "fuel tourism", as drivers from neighbouring countries, particularly Austria, take advantage of the lower, regulated prices here.
I think the worst part is carrying the two in your pocket at all times. Previously a gambler trying to quit could avoid specific locations. How the hell do you avoid the internet?
One of the best open-source tools out there. I'm a frequent user of Plex, Jellyfin, Tunarr, local music files, etc. I use it weekly to extract subtitles, trim videos, convert music formats, and remove audio tracks. After writing the previous paragraph, I realized I've never donated to the project; it's time to change that.
As a FFMPEG API user (e.g. through libavcodec etc.) I would definitely not say "simple". It's constantly breaking stuff and deprecating features from one version to another, and basically requires reading the source constantly to make sure of what's happening and on which backend / API each function can operate. Just today, when I was trying to implement vulkan video decode in ossia score (https://ossia.io) :
Copy data to or from a hw surface. At least one of dst/src must have an AVHWFramesContext attached.
int av_hwframe_transfer_data(AVFrame *dst, const AVFrame *src, int flags);
Well unlike what the very first sentence of the comment block hints towards, it actually is only implemented for host<->device copy, not device<->device for many backends
Big difference for ffmpeg especially (but I imagine for curl too): it's not just one guy in Nebraska. Seems to have a very healthy community of devs involved in it.
As a non-American, I find it interesting that so many comments in the thread insist that "No, American healthcare is not that expensive compared to that of other countries; no, the costs of the American healthcare system are not high due to greed and capitalism; and no, the American healthcare system cannot be cheaper or better, it is not perfect, but it works as it is."
As an American, I think most of my countrymen's arguments on the subject resemble something like "learned helplessness". The "healthcare system" is craptasm of kludges that each partly counter the fundamental irrationality of rapacious private healthcare but introduce their own idiocy. So the arguments and "ideas" involve this already dumb measure needs to be changed in that half-assed fashion. A few election cycles ago, an old woman was quoted saying "get the government out of my medicare [medicare is a state program, for foreigners trying to understand this stuff]"
For me, the best solution is a mixed one. My Plex has a curated list of tv shows and movies. Then I have Tunarr for "live" channels from own my selection. Best of both worlds.
It's a good test, no doubt. Many engineers are convinced that SaaS is practically dead, since all companies can vibecode their way to a lesser dependence on external (and paid!) software.
This take fundamentally misunderstands just about every aspect of running a successful software company. Today SAAS companies make 10x what the AI companies make in revenue. In 2 years time, this will still be true. In 5 years time, this will still be true. In 10 years time, this will still be true...etc...
The amount of time writing new code is a rounding error on the costs of a software business. Losing customers to bugs, downtime and other costs having to do with maintenance are far higher. Optimizing new code writing time at the expense of everything else is just foolish and only something that someone who has never run a software business could believe.
reply