I don't, but I sometimes see them used here in Japan. Some small-shop operators use them to add up charges and show the total to the customer. I was recently in the office of a small company, and I noticed that the bookkeeper had a calculator next to a pile of paper (receipts?) on her desk. She also had a computer in front of her with a spreadsheet on the screen.
When I moved here forty-three years ago, it was common to see abacuses used in similar situations. There's still an abacus school [1] not far from where I live, but it's been a long time since I saw one in use.
Back in the (early 1960s?) Isaac Asimov wrote a book on how to do arithmetic calculations in your head. He pointed out that someone who developed that skill could solve problems faster in their head than by reaching for a slide rule, and they wouldn't necessarily be limited to slide rule approximations. Engineers, accountants, etc. would be more productive by being able to do calculations without having to reach for a slide rule or pencil and paper.
[pause for 'slide rule' chuckle]
The same applies to "open calculator app and key the figures in," though. I'm not sure that "user interface" was a thing back when he wrote that, but that's what he was talking about.
That’s one reason the abacus hasn’t been completely replaced by calculators: some abacus users become able to calculate very quickly in their heads by visualizing the changing bead positions. In Japanese the skill is called 暗算 anzan, literally “dark calculation.”
(I'm in the US) I remember being taught how to use an abacus when I was in grade school. Not kidding. I'm not so old that they were used anywhere in real life. I believe the whole point was to teach different ways that calculating can be done. A little horizon expansion.
> Tell the agent your spec, as clearly as possible.
I have recently added a step before that when beginning a project with Claude Code: invoke the AskUserQuestionTool and have it ask me questions about what I want to do and what approaches I prefer. It helps to clarify my thinking, and the specs it then produces are much better than if I had written them myself.
I should note, though, that I am a pure vibe coder. I don't understand any programming language well enough to identify problems in code by looking at it. When I want to check whether working code produced by Claude might still contain bugs, I have Gemini and Codex check it as well. They always find problems, which I then ask Claude to fix.
None of what I produce this way is mission-critical or for commercial use. My current hobby project, still in progress, is a Japanese-English dictionary:
Great idea! That's actually the very next improvement I was planning on making to my coding flow: building a sub agent that is purely designed to study the codebase and create a structured implementation plan. Every large project I work on has the same basic initial steps (study the codebase, discuss the plan with me, etc) so it makes sense to formalize this in an agent I specialize for the purpose.
:-) I feel you. Perhaps I should have ended my post with "Would you like me to construct a good prompt for your planning agent?" to really drive us into the uncanny valley?
(My writing style is very dry and to the point, you may have noticed. I looked at my post and thought, "Huh, I should try and emotionally engage with this poster, we seem like we're having a shared experience." And so I figured, heck, I'll throw in an enthusiastic interjection. When I was in college, my friends told me I had "bonsai emotions" and I suppose that still comes through in my writing style...)
The article should have at least mentioned the contradiction between publicizing places whose business model is based on meaningful conversation and repeat customers to foreign tourists, who generally do not speak the local language and who are typically in the country for only a week or two.
You released it at just the right time for me. When I saw your announcement, I had two tasks that I was about to start working on: revising and expanding a project proposal in .docx format and adapting some slides (.pptx) from a past presentation for different audience.
I created a folder for Cowork, copied a couple of hundred files into it related to the two tasks, and told Claude to prepare a comprehensive summary in markdown format of that work (and some information about me) for its future reference.
The summary looked good, so I then described the two tasks to Claude and told it to start working.
Its project proposal revision was just about perfect. It took me only about 10 more minutes to polish it further and send it off.
The slides took more time to fix. The text content of some additional slides that Claude created was quite good and I ended up using most of it, but the formatting did not match the previous slides and I had to futz with it a while to make it consistent. Also, one slide it created used a screenshot it took using Chrome from a website I have built; the screenshot didn’t illustrate what it was supposed to very well, so I substituted a couple of different screenshots that I took myself. That job is now out the door, too.
I had not been looking forward to either of those two tasks, so it’s a relief to get them done more quickly than I had expected.
One initial problem: A few minutes into my first session with Claude in Cowork, after I had updated the app, it started throwing API errors and refusing to respond. I used the "Clear Cache and Restart" from the Troubleshooting menu and started over again from the start. Since then there have been no problems.
I used Claude Code just yesterday in a similar way: to solve a computer problem that I previously would have tried googling.
I had a 30-year-old file on my Mac that I wanted to read the content of. I had created it in some kind of word processing software, but I couldn’t remember which (Nexus? Word? MacWrite? ClarisWorks? EGWORD?) and the file didn’t have an extension. I couldn’t read its content in any of the applications I have on my Mac now.
So I pointed CC at it and asked what it could tell me about the file. It looked inside the file data, identified the file type and the multiple character encodings in it, and went through a couple of conversion steps before outputting as clean plain text what I had written in 1996.
Maybe I could have found a utility on the web to do the same thing, but CC felt much quicker and easier.
> I feel like I'm the only person on this site that doesn't use AI for coding.
I’m surprised by that. One reason I follow discussions here about AI and coding is that strong opinions are expressed by professionals both for and against. It seems that every thread that starts out with someone saying how AI has increased their productivity invites responses from people casting doubt on that claim, and that every post about the flaws in AI coding gets pushback from people who claim to use it to great effect.
I’m not a programmer myself, but I have been using Claude Code to vibe-code various hobby projects and I find it enormously useful and fun. In that respect, I suppose, I stand on the side of AI hype. But I also appeciate reading the many reports from skeptics here who explain how AI has failed them in more serious coding scenarios than what I do.
I wonder if the author’s use of “you” rubbed some people the wrong way: “You are alone and powerless. You encounter a deep challenge,” “When you let your thoughts wander, they take you on a journey you’ll never think possible,” etc.
The pronoun seems intended to refer to the author’s own experiences, but I can see why some readers might think it refers to them. I had a bit of a negative reaction to those “you”s myself, as I experience cafés very differently from the author.
I have a similar negative reaction to op-ed articles that use “we” to refer to some sort of personified zeitgeist. From some essays currently appearing in the Opinion section of the New York Times:
“We are all in a constant state of grief, even though we don’t always admit it.”
“But we spend much of our lives in weaker friendship markets, where people are open to conversation, but not connection.”
“Over the past six decades or so, we chose autonomy, and as a result, we have been on a collective journey from autonomy to achievement to anxiety.”
Oh, this one is difficult. I vacillated a lot in my early writing between I, we, and you.
Too many "I" sounds self-fixated and irrelevant for the reader. "You" is way too presumptive, unless addressing a specific person or specific group with actual evidence. "We" can also read as too presumptive, but I feel like it works in the case of processes the reader could volunteer to be part of. However, it must not be used to project emotions or experiences onto the reader.
For now, I've personally settled on "we" for most things (because the reader could hypothetically choose to follow along actively), but switching into "I" if I need to discuss something negative or a failing of my own. In other words, I would never project "a constant state of grief" on my readers – that I can only attribute to myself.
When I refer to something that cannot be experienced by myself, only by my readership (e.g. because it happens only to people who do not know where the article is going), I prefer "the reader" over "you", because while it might be true for the median reader, it might not be true for each and every individual reading.
I'm glad someone else also cares about this! I don't find it discussed very much.
(1) It starts out with "I" having trouble packaging – my readers are generally more intelligent and experienced than I am, so I won't assume they have the same trouble.
(2) Then we go into my experience, but phrased in a way where the reader could hypothetically follow along. Thus, I ask the reader to imagine "we" have a Perl script.
(3) Somewhere in the middle, the article refers to something that might be noticed by "the very attentive reader". I do not expect everyone to, not even the median reader, but I realise some readers might.
(4) The appendix contains a note in case "you" are very curious, because here I do address each and every reader individually.
That is commonly claimed, but it is thought by some to lead to unnecessarily complicated text. A tendency is also noticed for the passive voice to be introduced as part of such rules.
In case the irony isn't clear, I disagree. Clarity first, and stylistic choices after that.
Without knowing the author, I wonder if that's a natural construct in their native language. As I've moved from Canada, I find myself consciously having to check to see if I've written "I", or "one", given that my local language, places a preferred conjugation in the you imperative.
Coincidentally, Quebec uses "we" a lot in their ads, especially as a way to say "this is how things ought to be done". For example, "this December, we vote".
German also has "man" which almost directly translates to "one" (the pronoun).
Swedish also has the "man" and I hate when people use it to project feelings or experiences on me that I don't have.
I know for some people it's just how they speak – instead of saying "I get the urge to scream" they say "one gets the urge to scream" and they mean themselves only. But my computer-diseased brain interprets it literally and I get the urge to contradict them and say, "No, I don't!"
Personally I found the writing style unpleasant, because people on LinkedIn write the same way. I associate it to a specific kind of low-value content.
In this case, the use of "we" is also funny, because the opening sentence is such an unusual take.
When I moved here forty-three years ago, it was common to see abacuses used in similar situations. There's still an abacus school [1] not far from where I live, but it's been a long time since I saw one in use.
[1] https://maps.app.goo.gl/nvTg4hfSjTcba47c8
reply