0xCE0

As I see/understand it, there are only "native apps" (because native machine code is the only type of data computer can execute). There is also only one program running (OS, not counting bootloaders/firmwares), that reads executable files (e.g. for webbrowser, python) and then executes the parts of native machine instructions in it, and then programs can also run (but usually in more limited way) "computer code", that modifies the behavior of parent program (be it webbrowser/python etc.). Then the discussion probably goes to what is the difference between a "program/code" and "document" (program's file format, content state), and there are spectrum of static to dynamic content.

"Non-native" code performance is naturally one factor to consider, but access to freedom of computing is another. If/When we are already decided to stack programs running in browsers/mobile OS's, we have locked the freedom to computing on those stacks - yor code is not anymore in control, because the parent programs control how your program can behave. An in the name of security, access to parent program features might be denied or are behind paywall/insider-agreements.

Access to your data and programs is also important factor to consider. If you don't have your own data on your own computer/memory, you have nothing. Only expectations of accessing. But then the discussion goes to responsibility and self-sufficiency, so you must take responsibility for backups etc.

Another point to consider is non-native remote apps are easy way to force subscription-type of payments.

0

It seems that the "open access" is more marketing than something reality based they actually want to do.

https://dl.acm.org/openaccess ---> So how to access the content? Do I have to register or what? It the "open access" only for academic org's people or for everyone in the world?

https://dl.acm.org/ ---> Okay, nice simple search field without loggin in, but when you try to search something, you get thousands of results, even if you search specific author and the exact name of paper, you will get hundreds of results and the thing you want is buried somewhere on page 247. Filters of authors, years etc. are for Premium subscription. But just googling the thing finds the link to ACM... And want to get the actual PDF? Hope it says "free access"...

Maybe thinking in terms of your "obsession(s)" will lead to more clear and long-term answer. Obsession is something you love and hate at the same time, but still continue with it and in the end don't want to quit. Obsession also protects more strongly from loss of motivation and loss of "passion", because it tend to return you back to it again and again. It's like true love, which survives all the hardships.

The payment system is so critical to businesses that it should be forbidden to use AI for support issues. Besides payment systems are so niche/special, that there shouldn't be any "unnecessary" questions by customers (same kind criticality of function/communication as with accountant). Hope you get answer.

If the answers in this thread reflects the state of the art what "the advent of AI" as of 2026/6 has brought, I have to say that I am not amused. If we have this all-potential tool that can create anything, the potential is clearly capped by either people's ambition/imagination or the capabilities of coding agents... And please do not understand me wrong, I am just stating that I feel/think that the real-world examples of achievements should be something "next-level" stuff...

Anthropic user account system seems dangerous to begin with. Login only with email, which cannot be changed ("make new account if your email changes"). I have have monthly Pro plan which I cancelled immediately to avoid situation where banning leaves billing. Now they have changed so that I can't resubscribe monthly plan anymore (I have ~10 days left of previous subscription), only yearly billing is option for resubscription at this moment (and yearly commitment is a long time with AI models). When the subscription ends, we'll see what it is shows then... You can't trust these kind of businesses...

Trying to get my product (desktop application) to the state of minimal sellable version (according to my quality level expectations). I tend to be perfectionist, thinking it is never even good enough. Hopefully I can show it to you/world in the summer, and hear what people think of it. But for now (or the past 5 years), I have nothing to show and tell.

I actually downloaded and tried Zed first time about a week ago, because I needed a text editor that looks and behaves almost identically with Windows/macOS/Linux, so there is minimal switching hassle between developing for all these three OSs. And vims/emacs are no-choice for me, because if I don't use them for a while, I have to google how to exit/save etc. Not a choice for CEO.

I have now one week experience, and I like it very much. Some settings take a bit time to get right for my taste, and themes doesn't look polished, but otherwise it is excellent choice (even when thinking Sublime, which I considered the best of all). AI-things can be disabled for now, so let's hope it stays that way.

I also tried VSCode, and omg, I can't understand who want to use that... It is almost Visual Studio grade bad. At least by default settings. It couldn't even open 900 kb text file without freezing (Zed/Sublime had no problem, like 2026 computers/software shouldn't have with 1 mb file).

The job of hyperscalers is to scale and accelerate bills.

The answer is of course obvious, and applies to any business domain over time and hypes: how to sell, that is, being a real old-fashioned salesman, who has ability to make deals, who can bring money in.

I feel you. Booting selling is the most mysterious thing I know.

Unicode standard doesn't define any visual shapes for code points (except conceptual examples for some emoji-like symbols), so this is more some specific font's (that is not even mentioned/cannot be changed) glyph similarity visualization than anything to do with Unicode code point "visual exploration".

Linux is the only hope at this point for the future of computing.

Windows and macOS are just too risky to do any business with. Waste of all resources.

What you described is true, I also experienced this same:

https://news.ycombinator.com/item?id=46258982

Electron is business-friendly choice, because users do not refuse using it. It is users' fault. Users support and accept it by using it. Nagging doesn't change anything. As with every bad business, it is users who buy/use and therefore supports continuing its existence.

"Chaos isn't a pit, chaos is a ladder."

It will expand like JavaScript from its origins. It is now in its early period, like JS was before its standardization. It will become some sort of natural language source file format with fuzzy typing (vs HTML≈XML/JSON for structured document file format, JS for formal executable language source file).

Amazing, highly recommended. I have watched all seasons ~4 times. It has just some magical feeling, because tech is in the end about people and their interactions/dynamics.

And it shows. Desktop app gets laggier and buggier on every update.

And recently like 1 of every 10 consecutive songs just doesn't play. When clicking on the song, it feels like the app tries to redirect original song link (the "app" is a website) to some other link and it doesn't find it. As an example, Madonna - Frozen (from 1998 Ray of Light album) just doesn't play, just tried.

I have been paying Spotify customer since 2008 or something, I have playlists that are so old that it doesn't show dates added. Last week I cancelled my subscription, and switched to YouTube Premium (no ads + YT Music). YT music is even more horrible especially with playlists. Maybe I just buy somewhere (Amazon MP3?) my the 10 most listened albums and call it my music listening for the future.

Print to PDF + throw it to /TOREAD, which you will never open, but at least the content is there. Maybe add some relevant keywords in the filename (keep the original name also), so you can quickly grep/find what you need.

The point is to go beyond LLM training set. When the knowledge of LLMs, books, expert conversations etc. ends and cannot answer to your questions, you begin to feel where that boundary begins. From that line on, you are alone, and you can invent/discover something novel. Nothing is promised though, and it is the hardest thing to do, but at least the struggle gives a feeling of purpose.

To do quality QA/code review, one of course needs to understand the design decisions/motivations/intentions (why those exact code lines were added, and why they are correct), meaning it is the same job as one would originally code those lines and building the understanding==quality on the way.

For the terminology, I consider "vibe-coding" as Claude etc. coding agents that sculpts entire blocks of code based on prompts. My use-tactic for LLM/AI-coding is to just get the signature/example of some functions that I need (because documents usually suck), and then coding it myself. That way the control/understanding is more (and very egoistically) in my hands/head, than in LLMs. I don't know what kind of projects you do, but many times the magic of LLMs ends, and the discussion just starts to go same incorrect circle when reflected on reality. At that point I need to return to use classic human intelligence.

And for COBOL + AI, in my experience mentioning "COBOL" means that there is usually DB + UI/APP/API/BATCHJOB for interacting with it. And the DB schema + semantics is propably the most critical to understand here, because it totally defines the operations/bizlogic/interpretations for it. So any "AI" would also need to understand your DB (semantically) fully to not make any mistakes.

But in any case, someone needs to be responsible for the committed code, because only personified human blame and guilt can eventually avert/minimize sloppiness.

I really wouldn't want any vibe-coded COBOL in my bank db/app logic...

I feel this is a major turning point for how entities can/will behave from now on towards Trump's wants/decisions. Now it is publicly proved, that you cannot trust deals made with Trump, because they can be just invalidated at a moment's notice. Only bad deals to be made, so why would any reasoned entity agree to those. World will not take threats seriously any more, and will defend themselves.

Maybe missions in Venezuela, Iran etc. was accomplished so easily, that it blurred the judgment of what could be done. But those countries are different than a conglomerate of 450 M people / 27 countries. And now military and economic thinking/domains/threats were also mixed. "Weak EU leaders" can and are now forced to unite as one strong resistance.

Great ideas are cheap to copy but not cheap to generate (time-/skill-/moneywise). Execution has always some cost, and the cost trend is towards 0 (but not 0, because everything cost eventually and someone has to pay the amortized cost).

I'd say what matters again is authenticity, i.e. intentful design and intentful business==product(s). Businesses==product(s) that are created to respect the user, make their life (private-/businesswise) less sad. Giving prompt "make me a unicorn" isn't authentic/intentful business/product design. Real businesses==products have to prove their reason for existence (and keep doing it ad infinitum), so customers can trust them and keep them alive with cash flow.

If there is a bad business/product in market, in a long run it is buyers to be blamed, because they are the ones supporting its existence with cash flow. VC/loan cash can only give time==money for companies couple of years, because eventually someone has to pay the cost.

And I'd say the most "quality/intentful" products are not the ones that makes the most money on the market. One has to choose whether do design "The Witness" xor "Candy Crush Saga".

https://futuretextpublishing.com/ --> books vol 1-5

And what comes to original article, there is no "text [systems]" (or there is, like there are "number [systems]", just made up). "Text" like this very thing you are reading is 2D drawing. There are no character glyphs of any kind (latin, logograms etc.) defined by universe*, they are human invented and stored/interpreted at human collective level. Computers don't know anything about text, only "numbers" of some bit width, and with those numbers a system must be created that can map some number representation to some drawing in some method (e.g. with bitmap). Also there is a lot of difference between formal/executable and natural human languages. Anyways, it's not a about some text format/encoding, it's the human/computer defined/interpreted non-linguistical meaning behind it (Wittgenstein).

* DNA/RNA can be one such "universal character glyph/string", as the "textual" information is physically constructed and interpreted.

The exit of the company by the founders was definitely timely, if having assumption that SO can't be "relevant" anymore at the times of LLMs. Of course there is always value for human-to-human Q&A that goes beyond LLM training set, but that might happen now only at cutting-edge private environments/communities.

Slowly, but hurry, is my take.

Quality vs quantity of course depends on the nature of work. If you are employee and all the working infrastructure is ready there to be used, you can "just" focus on doing something, what ever it is. If you are employer, you can't "just" even go to the work, because you have to use unpredicted amount of time to figure out what you even need to do or have and why.

Whether you are employee or employer, make sure you feel the practical progress, that is, e.g. once a week you can have status session, where you can show that now you have something that you didn't have at last session, and that it is important step for the end goal.

Try to dig what a thing actually is, not what people say it is. Write down your current understanding with a date, so you can see years later how wrong or right you were. True learning is ugly route. Refine your own definition/understanding to be real-world bullet-proof. You need to be less-wrong over time. Use your bullet-proof learnings to build something, and don't let all the faux renduntant new ideas or manipulative generated comments destroy it.

Try to explode different things, so you can see clear boundaries of each separate thing and to minimize redundancy.

Try to map the depencency graph of a thing. Every higher level thing is a make file / spreadsheet cell DAG.