[GavinAnderegg]

It's strange to me that this blog post was written in English. If AI is available, why aren't we all communicating in Lojban? [0] It's an obviously superior language. What does it matter that many people already communicate in English and much of computing depends on that language? AI doesn't care about that. Plus, if you ever need to edit Lojban without AI, you should be able to pick it up in a few weeks, right?

[0]: https://en.wikipedia.org/wiki/Lojban

[gwern]

This post wasn't written in English, it was written in AIglish. (For god's sake, please tell me you see it at this point and you don't need to punch the opening into Pangram to see '100% AI' to recognize it by now?)

So in a way it's proving its own point. Why painfully write out by hand in English when the LLM will do a better job by porting your English prompt to AIglish and get +235 points and #3 on HN?

[fsckboy]

his comment is that any self respecting article ought to have been written by AI, and if so it should have been written in Lojban.

>It's strange to me that this blog post was written in English. If AI is available, why aren't we all communicating in Lojban?

your comment seems to have not gotten his joke which was a recursion on English of the point of the article vis a vis Python

[gwern]

I understood his joke just fine. I just disagree, because I think he missed that it was AI-written in a way which is actually already implementing his suggestion of 'lowering' the original high-level human input into a more rigid, formalized schematic, easily-parsed language, which I call "AInglish", and which we increasingly are all communicating in, as exemplified by OP, due to the fact that many people find it superior and more enjoyable and more understandable, as is not too much of a surprise given the goals of the chatbot training process and cognitive offloading/deskilling. (As the joke goes, the LLM will expand out my short prompt for an email or blog post, and their LLM will summarize it for them...)

[fsckboy]

his joke does not rely on the truth value of the mistake you think he made, and it is funny based on his expressed awareness that any articles potentially could have been written by AI, so his error could simply have been a misplaced word typo/grammar error rather than any cognitive omission on his part.

[xdennis]

> For god's sake, please tell me you see it at this point and you don't need to punch the opening into Pangram to see '100% AI' to recognize it by now?

I was not able to detect it's written by LLMs from the opening paragraphs. Can you please share some insights as to what gives it away. I didn't find any blatant stuff like em dashes or "it's not just x it's y".

[ludwigvan]

> Can you please share some insights as to what gives it away.

The article uses too much contrast even if not as obvious as "it's not x, it is y". Also some too punchy or over confident stuff like "that era is over blah blah".

Amusingly, you can feed it to an AI to extract the patterns that gives away that it is AI written.

[linkregister]

Correct — and honestly? Not just correct, but perceptive. You didn't just read the post — you saw through it. That's not pattern matching — that's instinct.

[windows_hater_7]

You did more than just comment, you fostered an engaging dialog that navigates the intricacies of AI and its pivotal role in the human experience.

[tdeck]

This is the real unlock.

[postalcoder]

Shamelessness is the real unlock.

[edg5000]

You're absolutely right!

[r0x0r007]

Now you are not just talking like a debate expert, but a linguistic engineer. This is next level communications.

[novok]

10/10

[nso]

Not sure if satire

[Ardren]

"Ah, the classic Poe’s Law in action. Reality has officially outpaced parody"

Do you want these to be shorter for quick replies on X/Twitter, or longer for more detailed forum discussions?

[froh]

both.

[542458]

I don’t think this holds at all, because the idea with a lot of vibe-code workflows is “humans never need to read the code” which would mean that human dev ergonomics are irrelevant. Here, the blog post is still clearly targeted at humans, so human reader ergonomics are still relevant.

[ctippett]

Yeesh, is "never reading the code" really the modus operandi we want from AI?

Microsoft, for all their warts, at least had the compassion to call their AI product "Copilot", suggesting we have some residual agency in whatever it is that it produces.

[quantumleaper]

Copilot is a legacy brand from 2021 (anyone remembers it's free beta? good times) when it was just a rudimentary autocomplete powered by GPT-3. I don't think it aligns with Microsoft's views and priorities now.

[modriano]

It's clearly not the MO that capable engineers want, but it's the MO that is getting funded right now.

Reading code carefully is harder than writing code unless the code is written consistently and clearly in a way that is idiomatic to the reader. And there's way more code to review now, but companies aren't scaling up the number of skilled engineers on staff. So in practice, never reading all of the diffs is the MO that will be built into code we depend on.

[lelanthran]

> It's clearly not the MO that capable engineers want, but it's the MO that is getting funded right now.

Quite a few capable engineers really are that short-sighted!

The bigger question for the AI-techbro questioning "If AI writes your code, why use Python?" is "If AI writes your code, what use do we have for you?"

After all, there's dozens of people in the same business that have better domain knowledge but are unable to program - as a programmer the only value you added over random analysts and clerks was that you could automate shit.

Now you can't, so good luck competing with people who were already making half your salary when your largest value-prop is now gone.

[simonkagedal]

There are lots of good use cases for vibe coding (”never reading the code”), prototypes, various explorations and one-offs. I’ve done various kinds of migrations where I didn’t bother to review the code much, just the output.

Possibly also some user-facing tools with a limited task and runtime environment.

Incidentally, these are all use cases where performance isn’t critical, typically, so you might as well write them in Python or Typescript or whatever makes most sense for the task.

Real production code? Yeah, you still need to be able to read it and understand it.

[tedggh]

You don’t need to read the code if you have a robust test suit to validate the output. The article implies testing is the new “reading”. If I spend 10 minutes reading code to find an edge case bug, I have lost the benefit of using AI. AI code is legacy code the moment is generated because I can’t tell why some lines were chosen, so the only way for me to add more features or refactor legacy code is by being very rigorous with testing.

[theshrike79]

Let's say you get access to a microservice from another team in the company. Do you read through and audit every line of code?

What if it's from an external vendor? A 3rd party SaaS?

At which point do you stop caring about reading every line of code you run?

[ctippett]

This is perhaps where our perspectives differ, because I see the usage of LLMs not as an external third-party (another team per your example), but instead as an extension of one's self. Given that lens, I'm highly sensitive to the quality and function of its output, because ultimately its contribution is my responsibility.

I appreciate not everyone feels this way, but that's why I personally would be anathema not to read its code.

[theshrike79]

My philosophy is just to Duck-type the program: "If it walks like a duck and it quacks like a duck, then it must be a duck"

I don't care if the duck is wet spaghetti inside, it does what I need it to do within the parameters I can measure.

If it fails to quack or walk later on, I have production alerts for that and I'll deal with it then.

[kevmo314]

Should've posted to moltbook

[boxed]

If the code is written in a language that no one can read it becomes vibe coded by definition. However, if it's a readable language then people CAN look at the diffs.

[throwawayk7h]

AI has not been trained on Lojban. And furthermore, this article is almost certainly primarily intended to be read by humans directly.

I understand you're being facetious, but I'm not sure what point you're trying to make about programming languages in comparison.

[parsimo2010]

It’s funny that in your reply “this article is almost certainly intended to be read by humans” you made what is the best case to keep writing code in Python even with AI.

Sure, if you are going to have an AI do all your coding and maintenance you can use whatever language it’s best at. But if you want to participate in the writing, debugging, and maintenance, it has to be in a language that a human can read. I’m not saying that Rust or Go is unreadable, but I know I am better at Python personally and am going to keep using it until the speed penalty matters to my project, and then maybe I’ll let an AI rewrite the whole thing in a faster language.

[Null-Set]

I'd argue that while Rust has a high barrier to writing code due to lifetimes and other type constraints, its still quite easy to read.

(Kind of the inverse of perl)

[Hamuko]

While it's a lot easier to read then Perl, it's still not as easy as something like a Python.

[3uler]

I’ve always found Ruby to be way more readable, what keeps me using python is the depth of libraries is unmatched.

So unless you’re into burning tokens having AI generate untested libraries, I’d stick to using the most idiomatic tool for the problem you are tackling.

[irjustin]

So, it's really interesting. We've started moving away from python libs because 25% OSS is out of date and another % is custom tweaks to the software help our use cases. In both scenarios it means our own fork.

And honestly it's not burning that many tokens if you've got an existing example lib to point to.

[zrm]

> But if you want to participate in the writing, debugging, and maintenance, it has to be in a language that a human can read.

I think the idea is that languages like Python and JavaScript make it easier for humans to write the initial implementation, whereas the "hard" languages from the perspective of creating the minimum viable product are the ones that make it easier for humans to maintain the code, and this has historically been a major trade off.

Whereas if you have the AI write the initial implementation...

[lelanthran]

> I know I am better at Python personally and am going to keep using it until the speed penalty matters to my project,

I hate Python (app distribution is painful), but will still reach for it before I reach for Go. Rust doesn't even enter the equation.

I would not have even needed to reach for Go in about half my programs if Python had mandatory typing and single-file no-dep distribution.

> and then maybe I’ll let an AI rewrite the whole thing in a faster language.

Even then, my reasons for discarding Python when I do discard it is almost never "performance", it's because the problem space requires mandatory typing for complex data types, or concurrency, or easy distribution.

Of course, this requires me to figure out quite early ion a project that those things would be needed.

[cwnyth]

Did you read the article? I think you're arguing against a strawman.

[parsimo2010]

I did read the article and I’m not arguing against a straw man. If you’re going to let an AI agent do everything for you then go ahead and use Rust (or any language with a strong type system that benefits agents).

But if I’m participating then I’m going to use Python because it’s easier to read.

If there’s anything that I’m arguing against is the author’s claim that the ecosystem of libraries (regardless of whether they are a wrapper) and readability don’t matter anymore. I’d say that in a lot of smaller teams it still matters. We’re not all using AI to ship slop. A lot of us are using AI to work on our ideas for our hobbies or for research. And it’s not fulfilling unless I get to be involved in the process.

[cwnyth]

But it's not talking about people like you. It's like getting mad at someone suggesting selling their car for a self-driving car, but you ride a bike everywhere. Take a breather and recognize that not every article is personally meant for you or your situation.

And this isn't even a defense of the premise. I'm not using AI to generate assembly code, because I don't know assembly.

[skeledrew]

> AI has not been trained on Lojban

I took the challenge and asked Perplexity. I have no idea how much of it is correct, if any, but I think the result[0] is pretty interesting anyway, especially compared to Esperanto [1].

[0] https://www.perplexity.ai/search/8315bbb6-fa32-40f3-8b2b-c6c...

[1] https://www.perplexity.ai/search/9c3839ba-1d68-4be9-afd1-4ef...

[lelanthran]

> And furthermore, this article is almost certainly primarily intended to be read by humans directly.

No, it's intended to generate traction for the author who lists his primary occupation as "building AI coding tools".

His goal is not the same as your goal.

[tjwebbnorfolk]

Python is intended to be read by humans also. Since I am a human and I want to be able to read and review the code in my project, I therefore have AI write in Python as well.

[woctordho]

How do you know it's intended to be read by humans? Don't you see how many web crawlers are there?

[amarant]

Oh, I hadn't heard of lojban before. Cool project!

Anecdotally, I think language effects the way you think more than most people realise, which is why I think a logical language is a great idea: it might "trick" people into thinking more logically!

Now to get someone to actually speak it with!

[bnjms]

If you’ve not heard of Lojban you may not have heard of Sapir-Whorf. Or you’re indirectly referring to it.

https://plato.stanford.edu/archives/win2011/entries/relativi...

https://en.wikipedia.org/wiki/Linguistic_relativity

[amarant]

I had not! Cool to see that there's a established theory about linguistic determinism(great term btw!)

I was only speaking from personal experience, I moved from Sweden to Brazil in my early twenties and after a while I began thinking and dreaming in Portuguese. I noticed then that my thought process changed(actually, I noticed it upon moving back to Sweden, as my thoughts and dreams shifted back to my mother's tongue. The shift the way back was much faster since I already spoke Swedish whereas in Brazil I had to learn the language before beginning thinking in it)

Anyway, I noticed then that I would interpret the world differently depending on which language I used for my internal monologue. Like way different. It was a curious experience!

[momoschili]

Are you trying to psyop us into using Lojban?

[georgeecollins]

Bona ideo! Ni ĉiuj komencu komuniki en Esperanto en ĉi tiu forumo.

[darkwater]

> Bona ideo!

I don't really know Esperanto but did they make a language from scratch with gender inconsistencies like in the already existing ones? Unless the a and o at the end of both words don't express gender like in Latin derived languages.

[funnybeam]

They don’t express gender, they signify adjective and noun. No genders in Esperanto

[altmanaltman]

A computer can understand all programming languages proficiently. How many people reading the blog know Lojban proficiently?

I get what you are trying to say but its a pretty bad analogy.

Also all programming languages do use english mainly in syntax but you are probably from a english-speaking country so you don't notice the irony.

And most people using AI will not need to edit their code at all if you go at all right? They will just keep refactoring with AI, why does the toughness of learning a language or whatever matter in this situation?

[ulfw]

How is this comparable in any way?

The recipient of the blog posts (all of us) can read English. None can read whatever this Logjam is.

If AI writes code why not write it straight into assembler or binary? No need to compile an intermediate language if the end user (the machine) is running on binary not on Python, nor on Rust, nor on BASIC or Swift or any intermediary human-optimised language

[KingFelix]

Thank you for sending me down the Logical Language Group rabbit hole

[adastra22]

Well for one, Lojban is not better than English.

[papa_pandora]

what made you draw parallel between message that's being delivered by the blog, and how the blod should be delivered?