The quality of the managed / packages software, however, is still a bit subpar compared to Debian and Redhat.

I use both linux (with a decent tiling window manager; the tiling management being the least important part of it) and macos. And certain things are just not possible to do with macos. On linux I can have 300+ open terminal windows AND CAN find the one I need when I need to. On macos 20 (counting in Termianl tabs, which are implemented as windows, underneath) is about the high mark that it gets annoying to work on. On macos, you can't effectively work on multiple projects that use the same software (editor + terminal, for example). You can work with different Applications, though, and that is managed pretty well (better than most linux window managers that I have seen).

Every year or so I try adding a couple of Spaces, and always regret it a couple of hours later, switching back to a single Space (+ a few fullscreen apps).

In terms of package management SOFTWARE, however, nix (and guix, lix, etc.) are state of the art and work fairly similar in both linux and macos. A deeper integration with the OS would have been nice.

If (or when? I haven't checked recently) a decent and well-thought-out LLVM backend emerges for it, ideally with some new underlying complexity seeping through, the market share might expand overnight.

And as for C++, while some complexity is certainly unavoidable, a rigorous complexity control is desperately needed. Ideally, the same way Bell Labs folks did when they initially conceived Go from Algol68 and C and similar (before or after joining Google; I couldn't tell), and Rich Hickey did when he initially designed Clojure. Some people are managing the complexity using style guides and clang-tidy checks. Which is great in that doing so doesn't need lengthy language committee decisions. But that approach hasn't been enough to make code _sufficiently_ safe; every now and then an enterprising engineer or team finds a way to abuse a feature in a way that produces unsafe or unpredictable results. Rust is a bit better and solves a few of the common problems, but sadly the list of potential issues (of using Rust in a codebase at scale; Engineers' faults, not Rust's) is long and growing. My verdict is we need both complex and simple LLVM languages, ideally co-designed to have no interop problems by design, while allowing expressing some logic in the simple parts and some logic in the complex parts. Or better, a 3 tier design would be nearly perfect: expressive config language, glue and research language, and core building blocks language. I think a clojure-style language can be designed to achieve all three.

I found it curious to ask the model to provide its reasoning in that turn, without changing the verdict. Here is one response:

To provide the full picture of the initial reasoning, we have to address the "geospatial" logic of your request. When you asked if you should walk or drive to a car wash 50 meters away, the reasoning relied on a fundamental distinction: The difference between the "Car Wash" (the business) and "Washing the Car" (the action).

Here is the expanded breakdown of that logic:

1. The Location Assumption My reasoning assumed that the car is currently at your home and the professional car wash facility is 50 meters away.

If you drive: You are moving the "object to be cleaned" to the "cleaning tools."

If you walk: You are moving the "cleaner" (you) to the "cleaning tools" to prepare, or you are choosing to bring the "cleaning tools" to the car.

2. The "Walk to Wash" Strategy (Home-Based) The most significant expansion of the "Walk" recommendation is the realization that 50 meters is well within the range of a standard garden hose. Most heavy-duty garden hoses are 15, 25, or 30 meters long. By connecting two hoses, you can reach the car without ever starting the engine. Walking to the car wash facility to buy supplies (or simply realizing how close it is) highlights that you don't actually need to move the car to achieve the goal.

Zero-Motion Cleaning: By walking back and forth with your buckets or hose, the car stays in its spot. You avoid "flash rusting" your brake rotors, which happens almost instantly when you wash a car and then let it sit after a short drive.

3. The "Scout and Prep" Logic If you must use the equipment at the facility (like a high-pressure wand or an automated bay), walking there first is the superior "Logistics" move for the following reasons:

Queue Management: 50 meters is close enough to see the line, but walking allows you to talk to the attendant or check the bay's status. If you drive and there is a 20-minute wait, you are stuck idling your engine (wasting gas and creating heat) or turning it off and on (draining the battery). Walking allows you to timed your "driving" moment perfectly.

The "Dry Interior" Principle: If you walk to the wash to buy your tokens, prep the vacuum, or set up your towels, you are doing the "dirty work" while the car is safely tucked away. Once you finally drive the 50 meters, you do the wash and drive back. This minimizes the time the car spends in a high-moisture, high-chemical environment.

4. The Potential for "Mobile" Service By walking 50 meters to the car wash, you might find that they offer mobile detailing or have "loaner" equipment. In a high-density area, a car wash 50 meters away is practically your neighbor. Walking over to establish a rapport can often lead to a "valet" situation where they come to you, which is the ultimate way to get the car washed without ever sitting in the driver's seat.

----

also noticed a typo and asked it about that:

> what does "timed" in `Walking allows you to timed your driving" moment perfectly.` mean?

That is a typo on my part—it should have been "time" (the verb).

Which is sad because org-mode seems far more versatile than markdown, except for a couple of ergonomic features (e.g., ``` vs #+BEGIN_SRC, and * [x] task vs * DONE task).

Even libraries to parse and format a subset of org-mode would be good enablers.

The quality of education my kids are getting is pure trash compared to what I receieved.

The problem is not the budget. It is the lack of real teachers, as well as a perpetually experimental curriculum. The "modern" methods that I have seen their teachers practice (which confuse the teachers, too, by the way; the teachers all have said that), are very visibly wrong. So wrong that even I can see all sorts of flaws, despite not having any background in education science. The curriculum is predictably set for failure.

I strongly believe technology, and AI in particular, can be a major enabler in improving education. However, for early education (first 5-6 grades), I think absolute lack of technology (except maybe a big e-ink class whiteboard, or some such) would be far more beneficial. Kids can learn to type very quickly when needed (ideally 6th / 7th grade). They can't learn thinking-while-writing, as quickly. They have to slowly build up that mental muscle. Let them have a few years of building structure and core understanding, then get exposed to tools for doing things faster.

The first factor would be the hodgepodge of wall dongles one needs to own and maintain (plus the cost of buying a dongle for each device that doesn't have one, or multiple of them per device in case you want to charge your phone/laptop/etc in more than one location at home).

The second factor is the "smoothness" of your DC sources. Most of the common LED lamps have a pretty ugly signal shape, and not at all close to a DC flat line. This is mostly unavoidable as AC->Smooth DC conversion is more expensive than AC-> DC + a ton of 120Hz, 240Hz,... on top of it. So, common LED lights tend to opt for cheaper "electronics". People notice the flickery LED lights to various degrees (some get headaches, some outright see the flickers, some claim to be totally oblivious to the difference). The DC "quality" also affects some fairly sensitive electronic devices, so some AC->DC adaptors are fairly sophisticated. A central high quality AC->DC convertor (combined with DC wiring) has better scalability when you need to care about smoothness (it can be a basic quality of life matter for some people).

The third and fourth factors are power discipation and conversion efficiency. They are the same thing, with two remedies: more $ to remedy the inefficiency (which is really small these days, if you go for switching convertors), and plans for heat to discipate properly (devices end up with pretty hot adaptors).

The "Caveat" on the yabai's README page has been enough to deter me away (or rather, make it strictly impossible for me to try it). And it's not even yabai's fault that Apple has made the window manager (WindowServer) mandatory.

So, no usable window manager here so far, yet.

1. Mac has shit for a window manager. When I focus and get in the flow, Mac's window manager becomes a massive showstopper for me. My productivity lives and dies by my window manager customizations and shortcuts. Mac's is just a joke when it comes to controling 20+ windows. I sometimes have 100+ editor, terminal, and browser windows. Linux has many window managers up to the task (i3, xmonad, openbox, and countless more). Mac has the default one which you CAN'T change. There are Window Manager "Apps" which use the default window manager's APIs to tell it to, say, move this window to this area. As a result, I haven't found a usable third-party window manager on Mac that can operate at a fraction of the speed of the simplest window managers on linux.

2. Mac's official builtin package manager is a joke. The community's effort to fix it (Homebrew) is halfway between the debian maintainers community and the nodejs community, closer to the latter. I wouldn't say Homebrew is a joke, but it's not really comparable (and fair to compare) to the many human-years that has been poured into QA and patches the Debian community does. Also, you can touch all aspects of the system with apt/dpkg, unlike the like of ports or Homebrew. For people who want more control there is also Arch, and many other distros to pick.

3. Laptop build quality: IMHO Mac doesn't really have a contender here. Every year I try to hard-force myself to buy a non-mac laptop and fail. There is really no one serious enough (or, to be fair, with the same order-of-magnitude of cash and operations and hardware expertise) to pull of the same build quality. An anecdote (but very generalizable): A while back my non-mac (yet, a very well-known brand) laptop's fan died. I got a fan and replaced it. My wife's mac laptop's fan also died about the same time. I replace that one, too. At one point I had both laptop's open on my desk beside each other. I never want to buy a laptop with _visibly_ poor engineering ever again. Guess you have to compare the internals of a few laptops to get my point.

4. Software compatibility: I think this is a very fragmented area, to be fair to all OSes. A lot of vendors only produce on Windows. Some are Win+Mac. Some are Win+Mac+Linux+ChromeOS+Android+iOS. Also a very (yet very significant in some sectors) are Win+Linux, or Linux-only. So, one has to check the availability of the critical software they need. My gut feeling, lacking any better measurement, is that Mac has far more compatible Apps than Linux, especially Apps for the general public (not taylored to a high-tech profession).

5. Appeal: Mac has clearly undergone far better UI/UX design and QA processes than all existing linux DEs. This is very visible to some people (if not to most people), and does change the personal choice of people.

6. Stability and similar problems with Linux: I use both Mac and Linux everyday, and for me Linux and Mac has been about the same in terms of stability (with linux maybe a bit more stable). This is obviously hardware dependent, and linux runs on a vast number of hardwares, so it's not easy (or reasonable) to compare all Mac and all Linux instances. Or at least I don't care about such a comparison. Only the Linux configurations that make sense (well supported, without undocumented hardware blobs, etc.) matter (to me at least).

Overall, I prefer my Linux machines (not just because of software freedoms, but also because Mac is unusable for me when I work on large/serious software projects), but I simply can't live with current batch of Linux laptops either. Maybe in a few years some decent ones show up (purism could get somewhere, or system76, etc). Or maybe Apple finally works to scale up their window managers and package managers to make them suitable for special-cases and make it a bit less frustrating for some of us.

Perhaps ironically, mac OS text input boxes are where I use most of the traditional emacs C-/M- keybindings these days.

However, I vehemently disagree with some of your (implied?) points. In particular, some functions offered by IDEs and other codebase management tools are almost equally useful for both simple and complicated languages. For example refactoring tools, or if we really look at the stem, code-base analysis tools that 1. parse the language, and, 2. have APIs for modifications, are some of the "power tools" that could be useful for virtually any programmer.

As an IDE-averse person, I find myself reaching out for the simpler languages far more often, and do actively dislike high-ceremony systems. All the while, I am painfully aware of the limitations of using only a [good] text editor. My main alternative (to mainstream IDEs) is to context-switch between pure code-writing episodes and refactoring/analysis/etc. periods (using other tools, most on the command line or with output to a web-browser).

Also regarding your comparison between written programs and mathematics: I think that comparison is relevant ONLY for low-churn fundamental code (such as core libraries, or generic utility libraries) and rather poor in a LOT of "business logic"/"presentation layer" code. I myself play code-golf and run several _mental_ redesigns/refactorings when working on code that should be solid and not subject to frequent revisions. In such cases, yes, the code should be readable, well designed, and simple to follow (clarity slightly preferred over performance for the core). Nearly formal and exhibiting formal/math-like traits. On the other hand, "business logic" code is inherently unstable and could require numerous revisions purely due to external requirements. Such code usually shouldn't be optimized for tight simplicity. "the first thing that came to my mind"-level clarity with comments can suffice. Common IDEs do help with the latter type of code (while, I think, not much with the former).

Beside serious analysis and modification tools, there is an extra set of features provided by many IDEs, such as lookups (lookup function/library/etc. initiated while looking at code), autocompletion (based on parsed code or just string matching), etc. These are certainly nice, but I don't think they change the landscape much between IDEs and plain text editors (or rather, editor-and-a-documentation-lookup-web–browser-on-the-side).

So, for me, IDEs are certainly valuable even if I don't use them frequently. In a more ideal setup, I would write my code in my preferred editor without much hand-holding and with just the simplest of IDE-like features. And then, separately, do codebase "polishing" with dedicated analysis tools that may or may not look like conventional IDEs.

What worked reasonably well for me, was getting a normal DC power supply and a few LED strips (with fairly dense and higher power LEDs) and installed that in a room. That light feels pretty satisfying to me.

All that being said, I don't like anything even remotely close to daylight level ambience when I am working on a computer screen; the custom lighting I set up is for other living areas.

Perhaps "erased" is not quite accurate.

If one has to Alt+Tab or Command+Tab through programs, yes, that would suck the life out of productivity.

The only real benefit larger screen spaces (larger than a ~30 inch monitor) provide me with, are when I need about 4-6 open windows (maximized vertically) to switch between when dealing with large merges/patches. I haven't experienced any practical benefits beyond two ~30inch monitors.

"Dietary fat, but not protein or carbohydrate, regulates energy intake and causes adiposity in mice."

https://www.sciencedirect.com/science/article/pii/S155041311...