"I Want to Wash My Car. The Car Wash Is 50 Meters Away. Should I Walk or Drive?"

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).

That won't change until top-notch, simple (i.e., without 100 transient dependencies) org parsing and formatting libraries for a few key languages (go, javascript / typescript, and python; maybe also C++ and java) become available.

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.

I think it gets away with being more verbose because those two aren't spelled "#+BEGIN_SRC" and "DONE", they're "C-c , q" and "C-c t d" (from memory). I think unless you really commit to learning a decent subset of what org-mode provides the ergonomics are always going to seem a little clumsy. I've always found emacs shortcuts hard to learn, and because of that I've never quite got my use of org-mode over the activation hump to really stick for the long term. Every time I leave it and come back to it I have to relearn a lot of it from scratch because there doesn't seem to be any sort of intuitive framework I can hang it all off.

I made my own macro* to encapsulate the currently selected text in SOURCE \END_SOURCE tags. Now you're telling me there was a keyboard shortcut for that?

What else I don't know about emacs?

*It was my first macro/function and while creating it I've learned that 1. It wasn't that hard and 2. With help of an LLM you can program emacs a little even without deep knowledge of elisp. Though LLMs suggest very unreadable elisp code and you have to rewrite everything.

The list of parsers is here: https://orgmode.org/worg/org-tools/index.html

I went to school in a poor country, and live in the US. The education budget was very low when / where I grew up, and it is pretty hefty where my kids go to school. I occasionally visit their school and volunteer to help. That has given me a good frame for comparison.

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 problem is not the budget. It is the lack of real teachers, as well as a perpetually experimental curriculum.

Taking this at face value: how are you teasing apart "lack of real teachers" from the budget? You don't think you'd get real teachers if there was a higher budget to pay them well?

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

How are you doing this comparison? Have you adjusted for cost of living and the alternative opportunities available to good teachers and such? I ask because usually people compare absolute amounts of money, which distorts the picture.

You say that in USA there are no good teachers because any that are good will find better-paying professions?

This sounds plausible. Like the previous poster, I have grown in an Eastern European country where everybody was extremely poor by today's standards. Education was not perfect and there were many mediocre teachers and even bad teachers.

However, there were also a great number of very good teachers, so there were good chances that you would happen to have at least a few good teachers. There were also many opportunities for the best students to learn beyond the normal curriculum, either by self-study in good free libraries or by attending special extra-curricular classes held by the best teachers for various sciences.

I have a lot of friends who have migrated to USA many decades ago. All of them complain about how bad is the education that their children are receiving, in comparison with what we had when we were young, which matches what the previous poster was saying.

While in the schools that I attended as a young child the teachers would have been considered very poor in comparison with any US teacher of today, in comparison with most other professions available at that time they had decent salaries, so indeed there were not many non-illegal alternatives that would have been a better career choice.

> You say that in USA there are no good teachers

No, that is not remotely what I'm saying. It's both entirely factually false and also a ridiculous extrapolation to make to a country of hundreds of millions of people.

> because any that are good will find better-paying professions?

What I am saying is that to the extent the parent may have encountered bad teachers (taking what they said at face value, whether it's accurate or not), this could be a big part of the explanation. i.e. I find it dubious that the budget would be unrelated to whatever they believe the teacher quality is. That's all I'm saying.

>You don't think you'd get real teachers if there was a higher budget to pay them well?

No, this has been proven many times that money is not a leading factor: Just one : https://eric.ed.gov/?id=ED418160

The only clear indication of student performance is parent participation and involvement.

> No, this has been proven many times that money is not a leading factor: Just one : https://eric.ed.gov/?id=ED418160 The only clear indication of student performance is parent participation and involvement.

No, we're talking about teacher quality, not student performance. Obviously they are not the same thing. You even listed some factors that affect them differently.

Which is often downstream of zip code.

> You don't think you'd get real teachers if there was a higher budget to pay them well?

Budget goes beyond teacher salary. It's also for giving teachers the tools they need, giving students the support they need, and schools the building maintenance that it needs. Good teachers can't teach and good children can't learn if they don't have the material, nor can they function well if their primary needs aren't met (well-fed, healthy, comfortable).

Power conversion efficiency is at best the 3rd or 4th important factor here.

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).

I use both. Here is my take on it:

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.

> 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.

This is so much my issue. I love i3wm, it's been a revolution for how I work. I never really understood the "desktop" concept with overlapping windows very much, and i3 works at an abstraction that is very close to how I imagine my desktop. I keep stacks of windows open in an arrangement that might be bizarre to anyone except me, but when I look at it it's 90% how I want it to be, a place no other WM/DM has ever gotten.

But I also don't want to deal with linux any more. Please don't sealion me with "but linux works fine for me!" here, but using linux feels like death by a thousand frustrations. Most recently I had to alias pulseaudio -k to pk because pulseaudio got out of whack so often I got used to killing it. That, plus I can't live with Ctrl-based shortucts anymore: I get serious pinky and wrist fatigue from a full day's work on linux. I can't be bothered to work around an entire missing staircase, so I switched back to macOS, where even if the WM isn't as good I can live with it.

(Incidentally, have you heard of yabai[1] / amethyst[2]? They're tiling WMs for macOS. I've been thinking of trying both out for a while now but I can't spare the time.)

1: https://github.com/koekeishiya/yabai/ 2: https://github.com/ianyh/Amethyst

I keep checking Amethyst every couple of years. Still not remotely comparable to i3 or other linux window managers. For one, it's extremely slow. I think it is about two orders of magnitude slower to say, move to another desktop/Space, than most (all I used, really) Xserver window managers.

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.

Ah, the SIP requirement for yabai isn’t that important IMO. They detail it in their wiki [1]. Incidentally, I tried it out since making the comment, and even without SIP disabled I’ve got it close to where I want it to be. It’s still not as great as my custom i3 setup was, but a few more weekends might get it to a much more comfortable place.

1: https://github.com/koekeishiya/yabai/wiki/Disabling-System-I...

This is a great, high effort post, and it matches my experience pretty well. Couple of comments:

> Laptop build quality

You're absolutely right here. When I had to take apart a MBP last year it was way easier than I expected from their reputation for being non-serviceable. I certainly wish parts weren't soldered on to the board, but that's an understandable tradeoff, maybe. I think my biggest point of criticism is the battery bags: pretty every older Macbook seemingly has had them expand somewhat, while I still have no issues with my Dell battery (in a solid plastic case that's externally swapable). The choice of Torx screws for the internals is fantastic as well. I'll never order a Mac for myself, but I am ordering Torx screws and the first thing I'll do with the next laptop I buy is going to be replacing all the internal Phillips screws with Torx for long term serviceability.

The externals are really important too: you're pretty much guaranteed to get a high quality screen with a Mac for example.

> Appeal: Mac has clearly undergone far better UI/UX design

Also agree strongly with this, although it's still messy and the inability to configure many things the way you can in Linux is a pretty unfortunate tradeoff. Tiny UX issues still bite: the global menu bar makes multitasking a pain because macOS desktops have a single application global context - you have to switch which application you're working on before you can do anything with it. Likewise, while you can usually maximize windows in macOS, practically speaking it's assumed you'll never actually do this. For example, the dock will change widths depending on how many apps are open, so "maximizing" is not really meaningful (the window size does not change when this happens).

> Software compatibility

This one's kind of messy, as you say. If you use mostly open source applications, there are a ton of them which are Linux-first or Linux-only. macOS has a weird problem where the norm is to sell every desktop application on a slick React website at about the $40 price point. Obviously, it's mostly closed source too. Though as a Linux user, if you need Photoshop, you've pretty much got to dual boot. That alone is an enormous negative in the compatibility bracket.

I have a mac pro and a lenovo carbon, build quality is on par with the lenovo being way more serviceable.

Heh, most of my emacs shortcuts start with ;

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

I'm not sure about the genetics of it (none of my family members seem to agree with me), but I also perform computer tasks far better in a dim light. A friend of me, who is also a night-owl, has the theory that when we get exposed to daylight, our cavemen heritage's natural reaction is to feel like going hunting/food gathering. While I don't buy the argument verbatim, I feel more like doing outdoor/physical activities on sunny days.

I kept seeing the following problem with several different LED lights we were installing until I found one that was better: Take your phone and take a video of the lights when on (normal framerate should be enough, try slow-motion for further investing). Most lights I got from the local hardware store were flickering quite visibly. And I'm pretty sure it's a design insufficiency of the adaptor electronics attached to it, not the LEDs themselves. If I were to guess I'd say most of them probably go the simple path of cutting off the negative half of the AC cycle and feeding the rest directly, without a decent low-pass filter to the LEDs.

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.

Not really surprising to some of us. Definers Public Affairs and a couple of other firms have been working hard for it. At some point the hacker news community might become more immune to paid-for opinion shaping, but that time is not now.