When using AI, I often find myself preferring either plain text (no markup whatsoever; just manual / text editor formatting of text blocks) or simple html to markdown, depending on the situation. To the point that I rarely see any point in using markdown for anything. If it is meant for to be a simple text mainly for human consumption, the markups often don't add much clarity (and often bring in an amateurish look, as if the author didn't know how to emphasize using English constructs), in which case plain text feels more pprofessional. If it is meant to be [lightly] processed before being presented to a human, or if it is meant to be processed by a tool / bot / LLM, then HTML is infinitely more straightforward.
Also I often call out my colleagues if they try to put a table in markdown. Markdown is not built for tabular data in most professional settings (i.e., one or two table cell could easily take a whole line of markdown to express). A basic <table><tr><td style="background: red">some number</td></tr></table> goes a long way.
I do get pleasure from typing out the code in some languages (and not in others; hello javascript, java!). Similarly, I love writing text with a calligraphy or fountain pen. However, I can't dedicate too of the much work / business time to whatever is more pleasurable.
So, I "doodle" some text / ideas / planning with a calligraphy pen, and type in some code, occasionally, both mainly for the fun aspects. There are side benefits to both, too. Writing some plans slowly and "beautifully" drags them out and I get to think longer on them, so the sporadic "nice looking plans" are often more well thought. And doing the coding all by myself stops my brain from losing the ability. I was initially in the 100% AI-writes-all-code camp for a while and noticed I am getting notably slow in some personal coding skills. It is too early to treat specs as the new code and old languages as assembly (but I admit we might get there some day).
In other words, I think AI doing 90-99% of the coding, depending on the language verbosity and AI accuracy for the code at hand, is quite reasonable.
Personally, this is an experience I thought about first before writing my comment. I think in the days pre-AI coding assists, I believe you describe the intrinsically human experience that's requisite to write code by hand. The wonder, the joy, the frustration, the confusion, the elation--the discovery. These days, the things I wonder about lie deeper and deeper behind more and more lines of code, through journey's that provide less and less joy, and thusly becoming more and more unreachable as I'm human, bound by an excess of things in addition to time. AI has helped me rediscover some of this sporadic creativity demonstrably due its ability to prototype recreational ideas on a whim
Professionally, I'm employed writing safety-critical avionics software. Superfluous amounts of cogent tooling putting guardrails on agents has enabled me to spend heaps more time to think deeply about how the software should work at a systemic level. The code by definition must be heavily criticized and battle-tested before it can go out the door to begin with. Albeit a beautiful part of coding, those sporadic bursts of creativity drive the code leaving my desk less and less, and I feel strongly that has made its quality paradoxically better since I'd spent much more time on broader implications and interactions.
This might have been the case a couple of years ago, but it is certainly not true any more, if you use AI [even occasionally] to manage some of your default.nix and flake.nix files. I learn by getting AI to edit it (default.nix for example), and then study what it did. It helps.
The quality of the managed / packages software, however, is still a bit subpar compared to Debian and Redhat.
Why would you use that feature? MacOS doesn't REALLY have multiple desktops (Spaces). That is merely a pre-release feature (for 10 years or so, I think). As evidenced by the many critical user journey bugs it has that don't get addressed.
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).
I've used spaces since 2013, they work well enough. The animation bug is annoying though. On displays higher than 60Hz, the animation is slower because they made it frame-based instead of time-based, or something silly like that.
I love the three finger gesture to move between them though, it's like moving pieces of paper around. You can also work around the bug I mentioned by swiping faster, but yeah I wish they'd just fix it so we can move on.
Of course it can be used. But it is very buggy (as in missing or not well-though-out behaviors), which is unlike the typical polish Apple human interaction folks deliver. For example switching between Spaces and then between apps and windows and creating a new app window don't work as expected in some combination of steps and for some apps. There are several other "corner" cases that show the features were not laid out in a full design to exhaustively decide the desired behavior in each case. Which is very much like when someone bolts on a feature to a system without fully nail down its interaction with all other adjacent and relevant features.
I'm just responding to your "Why would you use that feature?" question. I use it because I like it, and it works well for me. I'm not disagreeing that they have some bugs and design issues to work out. It seems pretty obvious MacOS doesn't get as much attention as iOS when it comes to these things.
Spaces help me visually organize related apps. I have all my chat apps in one, all my dev stuff in another.
I used to run Linux with i3 tiling window manager, but switched to Mac because the battery is so much better. Although the new Framework laptop looks like it has pretty great battery life.
Nix is not the same as nixos, and in this case the distinction matters. It has to step carefully around Apple's updates. This further highlights the fact Apple lacks the same quality package management as some linux distros. Nixpkgs (on macos), Ports, and Homebrew packages are toys compared to the EFFORT that goes into maintaining Debian and Redhat packages.
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.
Package managers are wonderful until you step near our outside of the packaged software - then you better hope you're on a big distro otherwise you may be in uncharted territory.
The current market share shows how far you can go with just being a better Java.
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 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.
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.
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.
> 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.
> 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).
Also I often call out my colleagues if they try to put a table in markdown. Markdown is not built for tabular data in most professional settings (i.e., one or two table cell could easily take a whole line of markdown to express). A basic <table><tr><td style="background: red">some number</td></tr></table> goes a long way.
reply