thw_9a83c

> want to reach all application windows with only the keyboard

So damn true. I never got the point of the MacOS windows management approach. It's a joke.

* Switch between non-minimized application windows: "⌘ + Tab" (but not between windows of the same application!)

* Switch between open windows of the same application: "⌘ + `" <- Yes, that's backtick, a different physical key depending on the keyboard language layout, WTF! (but doesn't work for minimized windows of that application)

* Switch between open and minimized windows of the same application: "Ctrl + ArrowDown" and use arrow navigation.

And yes, there's Exposé button/gesture, which, again, doesn't show minimized windows and doesn't work with an arrow navigation.

> The biggest improvement in Windows 11 is increased locking of small users into Microsoft ecosystem and Microsoft cloud services.

It is true that it was a major scam by Microsoft against its users when they forced them to sign into an online Microsoft account during the Windows 11 installation. Especially the stubbornness and determination with which they patch all the loopholes in the installation process (just to make it impossible to install Windows without an online account) is remarkable.

But in all fairness:

* Microsoft practically stopped charging users for upgrades since Windows 10. Windows 10 could be installed for free from older Windows, and Windows 11 is again a free upgrade from Windows 10.

* How many macOS users actually press "Setup later" when setting up a new Mac and use macOS without an Apple account? I think there will be very few of them.

> ...an LLM cannot recreate the community that has evolved around the library.

This is, in fact, an excellent point. You can ask an LLM to expertly clone or re-create any project in a different programming language. But that doesn't make you (or anyone else) an expert in that field, let alone competent in such a new codebase. Slowly developed, painfully debugged projects have a community of human brains who care about the topic. An LLM clone has nothing like that.

> Is C++ still relevant? What prevents Rust from completely supplanting it?

A highly mature ecosystem with well-established libraries. Especially in certain fields (DSP, robotics, CAD kernels, microcontrollers, etc.), there are no equivalent libraries and frameworks in Rust with such a proven track record.

Now, LLMs can rewrite those libraries in Rust quite easily. Such options weren't available a few years back. But it's still hard to prove that a rewrite hasn't introduced new bugs. It's easy to demonstrate that a piece of code has bugs, but much harder to prove that it doesn't introduce any new ones.

But the cheapest LTO-6 tape drive costs around €2,800. The Blue-Ray burner is around €150.

This is not very realistic. Recordable and rewritable Blu-ray Discs are a much more consumer/prosumer-friendly backup solution, and yet, due to low demand, the market is slowly dying. The market size for prosumer tape drives would probably be even several times smaller.

Yes, but first we need to figure out how to collect that new information. An efficient and ruthless data harvesting in one of the LLM labs secrets.

> Even if Deepseek v4.1 is the last open source LLM I have access to, I would be perfectly fine with that.

Your quantum engine aside, current open-source LLMs will not age well. They have a knowledge cutoff. If you ask them five years from now about something that didn't exist when they were trained, chances are they won't be able to provide a useful answer. They may still be useful for many applications, but their value will eventually deteriorate. Having continuous access to up-to-date open-weight LLMs is therefore about much more than simply having access to "better" models.

Yes, covered extensively over several few days.

There is a full Ars Technica article about this one [1]. Already posted to HN few hours before [2].

[1]: https://arstechnica.com/ai/2026/10/software-is-over-bold-ai-...

[2]: https://news.ycombinator.com/item?id=50000426

Interesting times. In the past, small software companies had to worry about big companies cloning their products overnight. Now, even the big software companies have to worry about LLM-driven imitators doing the same to them.

Yes, but those 10% of a problematic code is not easy to find without a very detailed study of the whole PR. And since most of the code looks (and usually is) very well-written, the human brain somehow doesn't expect to find those low-quality or sub-optimal parts in such code. That's why I wrote that reviewing the AI code requires different kind of attention.

> With AI, everyone’s output looks like a Ferrari, so it is hard to know what the internals are like.

Based on my experience, this is a significant issue with AI generated code. You wouldn't expect a real Ferrari supercar to have random internal mechanical components that are, for no reason, completely inappropriate for a high-speed car design. With AI generated code, such inappropriate components can appear randomly at any point in the implementation stack. And very often, they are deeply buried under non-trivial algorithms and are thus not easy to spot.

Fighting with a robot requires also a different kind of attention. When you're reviewing the human code, you can quite easily guess an overall seniority and competency level of the author and then you can adjust your level of attention to every detail. E.g. if the solution requires an understanding of some core idea, ones the human understands this core idea, you can be quite sure that it is consistently implemented everywhere. With AI, 90% of the PR could be expertly implemented but then, for no obvious reason, 10% could be low-quality surprise. I've never seen such unbalanced output from human programmers.

Definitely not "most people". I've checked the sources of this project and it is quite clear that author is now quite knowledgeable in a theory of computer programming languages. He definitely knows a lot about lexing/parsing, AST generation, type checking, bytecode etc. Most people have no idea and interest in such topics.

Yes, sometimes it does something unexpected when used as a tool for programming. And in that context, it is seen as an unwanted feature. In fact, that was my point. However, I disagree that it does a good job only "very very occasionally". That is not my experience at all.

We likes this "same, complex set of mannerism" when using LLM for programming. If you ask LLM to write a certain function for you, it gives you statistically obvious implementation. But maybe for writing an original book, this feature is not so desirable

This is really impressive work. Both RapidCam and the Cabinet Design Studio seem fairly polished already. I'd love to learn more about the process behind these creations.

Amazing job! The live editor capabilities are really well-thought. I've inspected the code briefly [1] and it seems that there is a fairly sophisticated domain specific parser which handles live updates, history tracking and WebAssembly hot reaload. It also uses AssemblyScript [2] as an intermmediate language.

I wonder whether all if this was implemented manually or with the help of LLMs. In either case, author has my respect.

[1]: https://github.com/loopmaster-xyz

[2]: https://www.assemblyscript.org/

The sad part of these cassette player remakes is that they don't have a Dolby NR (Noise Reducton) [1] system. I remember that without at least Dolby C-type NR, the sound from tape was really noisy. I wonder if the applicable patents have already expired.

[1]: https://en.wikipedia.org/wiki/Dolby_noise-reduction_system

From the article: In this article I’m not going to include the admittedly cool browsh, because...

These browsers are cool but I didn't know about browsh [1]. That one is also really cool. Thanks!

[1]: https://www.brow.sh/

> AIs (at the moment) don't learn.

Yes, and even when it learns (because there's new version of the AI model) it doesn't learn according to your company/team's values. Those values might be very specific to your business model.

Currently, AI (LLM) is just a tool. It's a novel and apparently powerful tool. But it's still just a tool.

Don't kill the messenger. I didn't say we shouldn't try. I'm saying that this will be a whack-a-mole problem and banning one mainstream service won't solve it.

> but the gym was a much better option.

If you live in a suitable city, there is an even simpler solution. Just walk to wherever place you need to go.

Unfortunately, the century of individual automobile ownership has made most cities unsuitable for this natural mode of transportation.

I think this is a lost cause. Even if the mainstream services are blocked or forced to comply, there will always be hundreds of lesser-known tools and services offering the same features. At this point, nobody has the power to close this can of worms.

Besides, who is going to decide when people's images are sexualized enough? Are images of Elon Musk in bikini alright because he's not a woman or a child?

> More or less the same thing.

Worse. The AI doesn't share any responsibility.

> Do you take into account the iPhone not holding the original images of every photo?

If you have enough storage space on your iPhone, you can select "Download and Keep Originals" in the photo app settings.

There is one class of languages missing in the comparison: Programming golf languages: E.g. Japt [1], Pyth [2] or Jelly [3].

Update: I noticed that the author mentions that "APL's famous terseness isn't a plus for LLMs." Isn't that just a design limitation of the LLM tokenizers?

[1]: https://github.com/ETHproductions/japt

[2]: https://github.com/isaacg1/pyth

[3]: https://github.com/DennisMitchell/jellylanguage

I think this is a lost cause. While the mainstream services may be blocked or forced to comply, there will always be hundreds of lesser-known tools and services offering the same features.

EMWM is really nice. Too bad that Wyaland will make alternative WMs like this one very hard to use and obsolete in the long run.

From the project describtion: "Looking for MAINTAINER for this project"

Honestly, Apple should officially maintain tools like this. However, for obvious reasons, such as the iCloud subscription revenue model, Apple will not do it. In fact, Apple may even make life harder for such tools.