[keiferski]

I bookmarked this comment a few months ago because I thought it was hilarious and increasingly accurate:

It's approaching a very strange situation where people make overly wordy and bloated AI generated content and other people try to use AI to compress it back into useful pellets vaguely corresponding to the actual prompts used to generate the initial content. Which were the only bits anybody cared about in the first place. One guy pays the AI to dig a hole, the other guy pays the AI to fill in the hole. Back and forth they go, raising the BNP but otherwise not accomplishing anything.

https://news.ycombinator.com/item?id=41635079

More seriously though; I wonder if/when we will reach a point at which asking for a Neuromancer-esque précis summary video of a topic will replace the experience of browsing and reading various sources of information. My gut feeling is that it will for many, but not all scenarios, because the act of browsing itself is desirable and informative. For example, searching for books on Amazon is efficient but it doesn’t quite replace the experience of walking through a bookstore.

[wcfrobert]

What that comment is describing is already here. A colleague sent an email that was obviously AI-generated (bloated, repetitive, low signal-to-noise ratio). I guess he's quite new to the team and it's a sign of formality, but I really don't mind if you send me just the bullet-point notes... Why are we going through this encoding-decoding process? I think succinctness and low-noise writing will be treasured in the age of AI.

[TeMPOraL]

> Why are we going through this encoding-decoding process? I think succinctness and low-noise writing will be treasured in the age of AI.

I hope so, because I hope this will lead to making it OK to skip the manual encoding process. After all, AI isn't doing anything new here - it's automating the customary need for communication to be in wordy prose paying right respects to right people. Maybe people will finally see that this - not AI, but the wordy prose part - is the bullshit that helps neither the sender nor the recipient, and it'll finally become culturally acceptable to send information-dense bullet point lists in e-mails instead.

[friendzis]

I don't see this happening. People learn wordy prose in education: an assignment requires certain amount of words, but the student is either unwilling or unable to come up with information-packed content and resort to padding with fluff. Some become copywriters, some middle managers, some HR. Eliminating fluffery makes these positions, built around wrangling as much written word as possible, suddenly obsolete and consequently people, because writing well masked fluff is their main marketable skill. There's very strong feedback loop working against information dense written word.

[wcfrobert]

Information-dense written words are beneficial in the corporate setting too. We just call them "executive summaries".

[_heimdall]

It's never been my read on people that wordy prose like this is done as a formality.

If a lawyer or am academic wrote it, it most often comes off as overly complex wording to prove a point of intellect or superiority.

For basically anyone else, when I see prose like that it most often reads like (a) they either don't understand the topic well or (b) they don't need to write it at all other than to stay busy and/or appear more valuable in a role.

[wcfrobert]

A well-written, well-formatted email does convey some level of professionalism right? Even if it is a little wordy. Maybe this is no longer true with AI.

I went to a career fair recently and a new grad sent me an email afterwards. His three-paragraph email can basically be reduced to "I want to work for this company. I am qualified. Please hire me". But I don't know how I would feel about that if someone actually sent me an email like this.

[_heimdall]

That's totally fair, there's a balance. Maybe a better argument I could make is that I find people often lean too far to the end of being verbose without any real reason to it. You may not want to be blunt or rude either, the balance is in the middle.

For the career fair grad you mentioned, a couple paragraphs would have been my expectation - three paragraphs isn't off base. If I were them I'd want to say I want to work for you, but I'd also want to at least mention why I want to work there and why you'd want me there. To me that extra context is a better email than just saying "hire me" in one or two sentences.

[tagami]

perhaps, but humans are human, and building relationships require a culturally appropriate carrier wave - especially in global work

[vidarh]

But if the message will be "decoded" by an AI, that "carrier wave" isn't from the original message anyway.

[wcfrobert]

Bullet point lists aren't always the most optimal. Anything longer than 6 bullet points actually reads worse.

[softwreoutthere]

Writing is an art, and some enjoy producing or consuming verbose prose. I hope AI doesn't change this.

Personally, I don't appreciate verbosity while reading blog or news articles.

However, I don't think its bullshit. If a author is sharing, they likely are doing so in a manner that they find enjoyable.

The way I see it, you don't need to read communications like this if you don't enjoy it. Much of what gets said repeats what has been said elsewhere.

[TeMPOraL]

- Correct re. writing as art - but context here is stuff like work e-mails.

- Such e-mails are in many ways similar to a comment thread like this -> my reply is a valid example of my point.

- I wrote the comment the way I actually think about this topic. Would it be better if expanded to full-blown prose?

- Alas, this doesn't fly at work (and rarely on Internet).

[neom]

If you look at that tech emails twitter account that shows emails from discovery in various legal things, this is basically what you see, just sentences of context with very little niceties.

https://x.com/TechEmails

[smeej]

I had a professor in graduate school who gave me permission to turn in my detailed outlines for my essays rather than filling in all the rest of the words. I think we both liked that better too, and that was 15 years ago.

[DanielHB]

It is really interesting because I have been using LLMs a lot for reading legalese documents. At least in the realm of Legal matters we already have this dynamic of "people make overly wordy and bloated LAWYER generated content and other people try to use LAWYERS to compress it back into useful pellet"

So at least for legal documents this LLM craze is a big improvement! It is much harder to out-spend other people on LAWYER stuff now.

[xnorswap]

In the case of lawyers though, it's more akin to paying someone to find and document edge cases.

That tends to end up verbose.

In the case of other realms, it's just padding because previously word-count was a metric used as a proxy for quality or depth of analysis.

[beezlebroxxxxxx]

In effect, we pay lawyers to be ridiculously pedantic for us where pedanticism is required or desired.

That level of pedanticism elsewhere, though, is incredibly annoying or precisely what is not desired.

[efitz]

I’ve wondered from time to time if we could replace some of the wordiness of laws and legal documents with bullet lists. For example, a trial about some interpretation of a word in a law could be contributed back to the law as a bullet point that says, “this also applies if …”.

[xnorswap]

What you're describing is law, most of it is bullet points, take for example the computer misuse act 1990, section 1:

https://www.legislation.gov.uk/ukpga/1990/18/section/1

Or if you're more patient, the whole lot:

https://www.legislation.gov.uk/ukpga/1990/18/crossheading/co...

It's all bullet points.

[FredPret]

> a trial about some interpretation of a word in a law could be contributed back to the law as a bullet point that says, “this also applies if …”.

Is this not what happens in case law?

[efitz]

The law doesn’t literally get updated with a bullet point. Subsequently attorneys have to do ever greater searches to analyze all the precedents.

[szundi]

I thought this is the case until I had an exit and I myself was actively participating adding to the contracts.

[WarOnPrivacy]

> I thought this is the case until I had an exit and I myself was actively participating adding to the contracts.

A couple of years prepping cases and docs for an attorney helped me appreciate the necessity of language in law.

Conversely, the lack of legal language gives us overly broad (abusable) laws. The CFAA is one notorious example.

[lolinder]

Obligatory warning: a lot of what seems like bloat in legal documents is there for a reason and has a specific purpose that your LLM isn't guaranteed to be able to handle. Sure, some lawyers add bloat just for the sake of it, but in many cases the text is there because it changes or clarifies the meaning of the surrounding document in a way that matters in court.

An LLM can probably help you understand the document if you're using it side by side with the real thing, but in this context it sounds more like you're using it to summarize.

[DanielHB]

I have been using it to ask questions about the document. For example I throw the document at the LLM and ask something and ask it to quote the original text. Then I ctrl+f the original text for the quote just to make sure the LLM is right.

[chaosite]

And in other cases the text is there because it has been used in other legal documents, and might not be needed for this document, but those documents were good and it doesn't cost anything to put that text in so we should keep using it.

In other words it's a cargo cult.

[lolinder]

The question is, do you trust an LLM to distinguish the cargo cult from the actually necessary text?

[red-iron-pine]

its use in the legal realm isn't new, and companies like @LegalDiscovery have been at this for years.

LLMs are more general purpose, and will probably eat/merge with that business.

[latexr]

> One guy pays the AI to dig a hole, the other guy pays the AI to fill in the hole. Back and forth they go, raising the BNP but otherwise not accomplishing anything.

Not accomplishing anything would be better than what is actually happening. Like with the hole example, once you fill it back up there’s a good chance you can still tell a hole was dug in that place.

What does “BNP” stand for in this context?

[JohnKemeny]

Norwegian, Danish, and Swedish all use BNP (Brutto National Product) for GDP. It could be German, although BIP is more common there (Brutto Inlands Product).

[axlee]

Could be a swede who meant "GDP" (BNP = BruttoNationalProdukten = Gross Domestic Product)

[globular-toast]

More plausible than "British National Party".

Does it raise GDP, though? I would have thought a more accurate thing to say is it raises the global temperature.

[taylorius]

>More plausible than "British National Party".

Maybe they were using Grok :-)

[vidarh]

Two units of work have been carried out, so yes it raises GDP.

[globular-toast]

GDP isn't about units of work, it's about the final product. So using two units of work instead of one to produce the same thing shouldn't affect GDP. But perhaps you are implying GDP is not correctly calculated?

[_heimdall]

That depends on how you're calculating GDP. If you are summing up all expenditures or incomes, the paid work done by each AI would be counted. If you're counting production, meaning the value added, it probably wouldn't count since digging a hole only to fill it back in created no value.

[vidarh]

GDP is about products or services. If someone is paid for digging a hole, then that a finished, delivered service. Filling it the same. If you dig and fill a hole without anyone paying you for either, sure it won't affect GDP, but if someone pays you, that the net result is no change does not alter the fact that you have been paid to dig a hole and to fill a hole.

The method used to calculate the investment can affect whether the income produced increase the GDP or whether only the consumption generated by that increased income is counted, but in a real-world scenario either alternative will increase the GDP.

> But perhaps you are implying GDP is not correctly calculated?

That GDP doesn't accurately reflect productive, useful effort for this reason has been a core part of the criticism of GDP since it was first formulated.

[dxyms]

Maybe GDP in german or dutch?

[ruune]

It's BIP, Bruttoinlandsprodukt, in german

[wsintra2022]

Business needs profit

[moffkalast]

Reminds me of this comic: https://preview.redd.it/v1ylid5639ra1.png?width=1024&auto=we...

In a culture where pointless busywork is seen as mandatory to appear proper, people will eventually automate it.

[WillAdams]

Rather than busywork, why can't we have a shorter work-week?

[cess11]

You might spend that extra time improving your life or start organising with people in the workplace, and also possibly consume less and have more experiences.

[rahoulb]

I feel the real problem comes when people stop publishing on the (open) web because 1) no-one is reading it directly and 2) they know their hard work will just get slurped up and regurgitated by LLMs.

[majormajor]

For things like reviews I usually get a lot more value from a quick manual scan than an AI overview of any given review. Summaries of many reviews could be useful but if there are, e.g., thousands of reviews, I find myself skeptical of how truly "thorough" or well-executed that AI summary is anyway.

For "how do I write a bash script that will do X" the AI summary currently is way better than scanning a handful of StackOverflow tabs, already.

It will be interesting to see how "fresh" things like that stay in the world of newer or evolving programming languages. This is one of the areas where I already see the most issues (methods that no longer exist, etc).

[throwup238]

I think we’re still missing a breakthrough in synthetic data generation for code in order to LLMs to come into their own. Something can ingest the documentation of all the different ecosystems and generate fine tuning to improve the accuracy of recall.

[_heimdall]

LLMs may get there when real reasoning is figured out, I'm expecting that to require a totally different approach used in combination with LLMs as the language unit.

Do we really want that though? As soon as these systems can reason through software problems and code novel solutions, there is no need for humans to be involved.

Likely we couldn't be involved at all, those systems would come up with solutions we likely would have a hard time comprehending and it would be totally reasonable for the system to create its own programming language and coding conventions that work better for it when the constraint of human readability is removed.

[red-iron-pine]

> It's approaching a very strange situation where people make overly wordy and bloated AI generated content and other people try to use AI to compress it back into useful pellets vaguely corresponding to the actual prompts used to generate the initial content. Which were the only bits anybody cared about in the first place. One guy pays the AI to dig a hole, the other guy pays the AI to fill in the hole. Back and forth they go, raising the BNP but otherwise not accomplishing anything.

Dead Internet Theory in a nutshell.

https://en.wikipedia.org/wiki/Dead_Internet_theory#:~:text=T....

[larodi]

W.Gibson and N.Stephenson have proven right for so many things, like we live in their books. I wouldn't be surprised if they got this one right also, and it sounds plausible.

Buuut, then, still, my significant other loves watching Friends, which was released she was born, and is not rewinding. So it depends.

[gotoeleven]

And this state of things may not be that bad in and of itself but it will make the airbrushing of various topics for propaganda or therapeutic purposes very easy.

[SketchySeaBeast]

Saying it only raises the BNP is incorrect - it also generates waste heat and carbon dioxide.

[Cthulhu_]

For shits and giggles, I passed that quoted paragraph into chatgpt to expand it to make it overly wordy and bloated (but limited to three paragraphs because I have limited patience), and also to compress it down to a single sentence:

> We are increasingly finding ourselves in a peculiar situation where the use of artificial intelligence is creating an ironic cycle of excess and reduction. On one side, AI is being employed to generate content that is often overly verbose and bloated, as algorithms churn out text that fills space rather than conveying concise or meaningful information. This output, while perhaps technically impressive in its sheer volume, often fails to serve the core purpose of clear and direct communication. It may contain a great deal of data, but much of it is irrelevant or overly embellished, making it difficult for the reader to extract anything of value. Essentially, the AI is tasked with expanding ideas into sprawling narratives or articles that only obscure the original intent.

> On the other hand, there are those who are now turning to AI to reverse this inflation, trying to distill these bloated pieces of content into more digestible, efficient versions. These AI-driven tools aim to compress the original text, stripping away the superfluous language and presenting a more focused, streamlined summary that more closely reflects the essence of the original prompt. However, this approach often feels like a futile exercise in trimming down something that was never necessary in the first place. The irony lies in the fact that the only parts people ever truly cared about—the core ideas, the relevant insights, the key messages—were buried under layers of unnecessary verbiage in the first place, only to be painstakingly uncovered and reorganized by another layer of AI intervention.

> In a sense, this back-and-forth process resembles an endless cycle of creation and destruction, where one person pays an AI to dig a hole, and another pays it to fill the hole back in. The end result may look like progress on paper—content is created, then refined, revised, and streamlined—but in reality, very little of substance is actually achieved. The net effect is often minimal, with people endlessly tweaking and refining information, but ultimately not advancing the core objective of clear communication or meaningful progress. This cycle may inflate the BNP (bloat-and-purge narrative process) without producing any tangible results, leaving us with more text, more noise, and less clarity than we had before.

And reduced again:

> The current trend sees AI generating bloated, verbose content that others then compress back into useful summaries, creating an endless cycle of inflation and reduction that accomplishes little beyond adding noise and complexity to what was originally a simple idea.

[InDubioProRubio]

Its going to be the "Melons rot in the warehouse as the central committee can not come up with a distribution plan" moment of capitalism. Which of course is not a pure, real ism, while being as pure and real as an ism, as it gets with humanity as executing virtual machine.

[evertedsphere]

It's approaching a very strange situation where people make overly wordy and bloated AI generated content and other people try to use AI to compress it back into useful pellets vaguely corresponding to the actual prompts used to generate the initial content.

ah yes the reverse autoencoder

[malermeister]

So basically, lossy compression at a huge energy expense. Thanks, AI geniuses!

[px43]

Isn't this an advancement in communication though? People can put out a message in whatever language or style they prefer, the machine translators translate it into an overly verbose AI vomit, and readers condense it back down into the exact kind of personalized language they're wanting to consume.

[keiferski]

Depends on your theory of communication, I guess. If it’s to get the most tailored message possible, then yeah it is an advancement. But if it’s about communicating authentic feelings/thoughts between two people, then it’s a big step backwards. This might not be super relevant for random website content, but if for example people start using generative AI to communicate with each other, I think it will feel very alienating.

[mtnGoat]

I got a thank you email the other day after a meeting that was clearly written by AI, it was a real turn off. English was the authors second language, but she does public speaking in English, so I know she has decent command. Regardless, id still rather get an authentic heart felt thank you in broken English then a fake one. It comes off as inauthentic.

[generalizations]

It's exactly the same as using a complex networking protocol to transmit a very simple text string across the internet. There's reasons why it's efficient, and ignoring them is like asking why we can't just netcat from local ip to local ip. Ceremony is, unfortunately, necessary, as is preserving formalities and egos.

[gherkinnn]

It is both lossy and takes up more space, how is that an advancement?

[delusional]

"Communication" isnt about "personalization" when i communicate with you, I'm not looking for you to tell med what i already know. Im looking for you to tell me what YOU know in the style YOU want.

[OJFord]

I think it's strictly worse than Google Translate-ing your bullet point notes?

[taylorius]

No, because it's an inauthentic message. Your're speaking to your AI, like a politician who only hears about developments from his advisors. How can he know if he's getting the real truth of things?

[exe34]

that's an interesting idea, we might get to hear what we want. it's like when you tell a manager "yes it would work that way but it would require more time", they hear "yes that's fine!"