• JackbyDev@programming.devEnglish
    10·
    6 hours ago

    I’m still mad there’s no straightforward way to convert a PDF into semantic HTML. There’s plenty of tools to convert it into HTML that looks the same with pages and such, but I just want the content.

    • AnimalsDream@slrpnk.netEnglish
      3·
      5 hours ago

      Would it work to convert it to a simpler intermediate format like rtf or txt, and then convert into html? Why html anyway, Isn’t epub more appropriate?

        • AnimalsDream@slrpnk.netEnglish
          1·
          11 minutes ago

          Yeah I get that. I’ve just gotten used to leaving pdfs the way they are, and choosing to read them on more appropriate devices like laptops or tablets.

  • GroundedGator@lemmy.world
    91·
    7 hours ago

    We absolutely should have more specialized LLMs. That being said we have dozens of tools that convert documents and data. Also any engineer worth a nickel should be able to whip something up in an hour or so for most cases.

  • Gsus4@mander.xyz
    17·
    7 hours ago

    Same for music like suno. I don’t need to remix and hallucitate new fusion music, I just need a really good way to effectively search/discover all music that already exists in one place.

      • Gsus4@mander.xyz
        5·
        6 hours ago

        When I give suno a prompt for “electrojazz metal microtonal polyrhythmic” I get a fusion remix that sounds good, but sometimes it sounds just like a plagiarized remix of something someone created before.

        But search in Spotify will not give me good results if I search for that. It’s just the search that needs to become better for discovery, because the song type already existed to train suno, it is not truly creative.

        Which is funny, because it should be faster, easier and cheaper to create a good search and discovery engine instead of training and implementing brute-force AI. Especially because there is so much music that there has to be some sample left when you search, but it needs to be less rigid…

        tldr: I want spotify to be better at finding songs from a prompt than suno is at making a new song plagiarized from unmentioned influences.

        • emeralddawn45@discuss.tchncs.de
          4·
          3 hours ago

          Its been a long time since ive used it but last.fm might be better for discovering obscure genre types than spotify. Spotify wants to generalize and distill their recommendations as much as possible because they want to appeal to a broad audience but iirc last.fm uses user tags to classify the music so its more likely something is tagged with the obscure search terms you’re looking for.

        • e8d79@discuss.tchncs.de
          2·
          3 hours ago

          The sad thing is that machine learning methods are actually pretty good at classifying data. So Spotify could implement an “AI” enhanced search that works with your search terms if they wanted. Unfortunately, they no longer seem interested in improving their product.

          • AugustWest@lemmy.world
            2·
            5 hours ago

            I think the miscommunication here is in the function. I agree with you, that you can use Spotify to find all kinds of music, and even incredibly niche music if you dig around. What the user you replied to wants is to be able to find that incredibly niche/hyper-specific music with a single search query.

            If that user wants to discover music like the band Tool, but has never heard of the band Tool, they want to be able to type “complex polyrhythmic prog metal with tribal trance undertones” and have it spit out Tool, Lucid Planet, etc. Spotify can’t do that. Tool is popular enough where it isn’t a great example. But even still the best you could do is look at their curated lists for prog metal and polyrhythm and come up with what you want after skipping through some bands. And you would find things like Dream Theater and Periphery on those playlists which couldn’t be further apart from Tool and each other, despite sharing a general genre.

          • endeavor@sopuli.xyzEnglish
            10·
            11 hours ago

            If you love ai trash and stock presented as big artist in order to cut revenue from everyone not part of the label cartel, then sure spotify is the best.

  • jonne@infosec.pub
    571·
    23 hours ago

    So I guess it’s just only us Millennials that know how to convert a PDF properly, and we’re just sandwiched in between boomers and gen Z finding the most ridiculous ways to try to accomplish that task.

      • ikt@aussie.zoneEnglish
        16·
        13 hours ago

        real men find a random pdf converter website on the internets and upload our secret documents there

      • lime!@feddit.nuEnglish
        141·
        2 hours ago

        $ pandoc doc.pdf -o doc.txt

        Edit: welp, pandoc can’t do that. pdftotext it is.

        • mexicancartel@lemmy.dbzer0.comEnglish
          1·
          6 hours ago
          magick file.jpg file.html

          Imagemagick be converting anything into anything (Actually in this case, it make an html file and a png file which is referenced in html file and html page displays it)

          • lime!@feddit.nuEnglish
            1·
            4 hours ago

            not really a good way to get the text out of a pdf though. then again, turns out neither is pandoc.

    • dan@upvote.au
      373·
      23 hours ago

      Somehow, millennials ended up being the only generation that at least kind of knows how to use computers.

      • Saleh@feddit.org
        131·
        12 hours ago

        Naah. There is plenty of Gen X, Y, Z who know and plenty of Millenials who dont.

        Its just if you wanted to “do stuff with computers” you had to develop some understanding back then.

        Today you can “do stuff” like gaming much easier out of the box. So not everyone who “does stuff” knows his way around.

        In the office most colleagues of all generations just know how to do their specific things, mostly in MS Office products.

        • Tuxman@sh.itjust.works
          3·
          3 hours ago

          Of god…. The number of colleagues that their WHOLE job depends on MS Word and they never heard of “Insert page break”………

          Then they complain when inserting an image breaks their whole document…….

        • SpacetimeMachine@lemmy.world
          4·
          8 hours ago

          The difference being that a lot of millennials know how to figure out how to do stuff on computers by doing basic research. I’ve found a lot of my Gen-z friends to be more helpless in that regard.

      • Flying Squid@lemmy.world
        4·
        13 hours ago

        I was probably using computers when you were still in your mom’s ovaries. My first one was an Apple ][+ in 1982.

    • Litanys@lem.cochrun.xyzEnglish
      115·
      21 hours ago

      This is why millenials, despite all else wrong with us, are the best generation. I asked a kid the other day if they knew what a directory was… Crickets.

      • DragonTypeWyvern@midwest.social
        71·
        14 hours ago

        What’s fucking wrong * is * that we’re sandwiched between Boomers/GenX and Zoomers. Too young to be able to shove the Cold War brain rotters out of power, too old to convince the Zoomer incels to talk to a girl instead of listening to Andrew Tate.

  • SkybreakerEngineer@lemmy.worldEnglish
    2062·
    1 day ago

    You can’t parse [X]HTML with LLM. Because HTML can’t be parsed by LLM. LLM is not a tool that can be used to correctly parse HTML. As I have answered in HTML-and-regex questions here so many times before, the use of LLM will not allow you to consume HTML. LLM are a tool that is insufficiently sophisticated to understand the constructs employed by HTML. HTML is not a regular language and hence cannot be parsed by LLM. LLM queries are not equipped to break down HTML into its meaningful parts. so many times but it is not getting to me. Even enhanced irregular LLM as used by Perl are not up to the task of parsing HTML. You will never make me crack. HTML is a language of sufficient complexity that it cannot be parsed by LLM. Even Jon Skeet cannot parse HTML using LLM. Every time you attempt to parse HTML with LLM, the unholy child weeps the blood of virgins, and Russian hackers pwn your webapp. Parsing HTML with LLM summons tainted souls into the realm of the living. HTML and LLM go together like love, marriage, and ritual infanticide. The <center> cannot hold it is too late. The force of LLM and HTML together in the same conceptual space will destroy your mind like so much watery putty. If you parse HTML with LLM you are giving in to Them and their blasphemous ways which doom us all to inhuman toil for the One whose Name cannot be expressed in the Basic Multilingual Plane, he comes. HTML-plus-LLM will liquify the n​erves of the sentient whilst you observe, your psyche withering in the onslaught of horror. LLM-based HTML parsers are the cancer that is killing StackOverflow it is too late it is too late we cannot be saved the transgression of a chi͡ld ensures LLM will consume all living tissue (except for HTML which it cannot, as previously prophesied) dear lord help us how can anyone survive this scourge using LLM to parse HTML has doomed humanity to an eternity of dread torture and security holes using LLM as a tool to process HTML establishes a breach between this world and the dread realm of c͒ͪo͛ͫrrupt entities (like SGML entities, but more corrupt) a mere glimpse of the world of LLM parsers for HTML will ins​tantly transport a programmer’s consciousness into a world of ceaseless screaming, he comes, the pestilent slithy LLM-infection wil​l devour your HT​ML parser, application and existence for all time like Visual Basic only worse he comes he comes do not fi​ght he com̡e̶s, ̕h̵i​s un̨ho͞ly radiańcé destro҉ying all enli̍̈́̂̈́ghtenment, HTML tags lea͠ki̧n͘g fr̶ǫm ̡yo​͟ur eye͢s̸ ̛l̕ik͏e liq​uid pain, the song of re̸gular exp​ression parsing will exti​nguish the voices of mor​tal man from the sp​here I can see it can you see ̲͚̖͔̙î̩́t̲͎̩̱͔́̋̀ it is beautiful t​he final snuffing of the lie​s of Man ALL IS LOŚ͖̩͇̗̪̏̈́T ALL I​S LOST the pon̷y he comes he c̶̮omes he comes the ich​or permeates all MY FACE MY FACE ᵒh god no NO NOO̼O​O NΘ stop the an​*̶͑̾̾​̅ͫ͏̙̤g͇̫͛͆̾ͫ̑͆l͖͉̗̩̳̟̍ͫͥͨe̠̅s ͎a̧͈͖r̽̾̈́͒͑e n​ot rè̑ͧ̌aͨl̘̝̙̃ͤ͂̾̆ ZA̡͊͠͝LGΌ ISͮ̂҉̯͈͕̹̘̱ TO͇̹̺ͅƝ̴ȳ̳ TH̘Ë͖́̉ ͠P̯͍̭O̚​N̐Y̡ H̸̡̪̯ͨ͊̽̅̾̎Ȩ̬̩̾͛ͪ̈́̀́͘ ̶̧̨̱̹̭̯ͧ̾ͬC̷̙̲̝͖ͭ̏ͥͮ͟Oͮ͏̮̪̝͍M̲̖͊̒ͪͩͬ̚̚͜Ȇ̴̟̟͙̞ͩ͌͝S̨̥̫͎̭ͯ̿̔̀ͅ

    • locuester@lemmy.zipEnglish
      81·
      16 hours ago

      This is a primary use for me. A couple times per day.

      That’s part of what makes LLMs so popular with software engineers, they solve lots of trivial daily computer tasks.

  • wise_pancake@lemmy.ca
    331·
    1 day ago

    Yes, there are LLMs for that, you literally just have to Google “llm parse PDF”.

    You could also use tesseract or any number of other solutions which probably work as well…

    But an inexperienced kid is gonna act like an inexperienced kid

    • mrkite@programming.dev
      20·
      24 hours ago

      But an inexperienced kid is gonna act like an inexperienced kid

      Let’s give him access to government payroll!

    • JohnnyMac@lemmy.world
      427·
      1 day ago

      Doge aside, He’s a kid that won prizes for writing ml models to parse greek letters from unreadable ancient ashen scrolls. Inexperienced? You sure?

      • palordrolap@fedia.io
        211·
        1 day ago

        It’s kind of easy to forget about or ignore any experience they might have if they’re asking questions like that. Sure, maybe it was a brain fart from a panicked intern who’s having orders barked at them from a powerful individual that they want to impress, but that doesn’t make it any better, does it?

        • JohnnyMac@lemmy.world
          313·
          1 day ago

          Or he’s asking a more nuanced (or poorly worded) question than people in this thread are assuming.

          • MadhuGururajan@programming.devEnglish
            31·
            8 hours ago

            if you can’t explain your problem and expect people to read between the lines then don’t be surprised people assume the unspoken parts. we’re not oracles here!

          • andyburke@fedia.io
            22·
            1 day ago

            … which would be?

            Because to me it looks like someone asking to use an LLM to parse things that were created to specifically be parsed by machines. Looks like someone who doesn’t know what the fuck they’re talking about. I’m open to being educated on what that subtle question you’re referring to might be, and how this person is somehow experienced and being nuanced, just drop it on me.

            • dependencyinjection@discuss.tchncs.de
              7·
              11 hours ago

              Exactly. I’m a software developer and I wouldn’t ask this question on Twitter. Although I might not remember how to convert files from one format to another off the top of my head. I would just use a search engine or ask my boss or even ChatGPT. It would take me a couple of minutes to learn what tool I need to do it.

            • andyburke@fedia.io
              8·
              1 day ago

              I mean … this person works for the department of government EFFICIENCY, right?

              <amidala face>

              • JohnnyMac@lemmy.world
                36·
                23 hours ago

                I get it. He’s a traitor. He’s evil, and he should be in prison. The pitchforks are out and people want blood. I actually agree.

                But to insinuate he’s a mouth breathing idiot that doesn’t know what LLMs or AI is, by ignoring the fact that he won prizes by solving problems that no one had solved before is just disingenuous. Oh, and that he solved it by creating his own ML models. But, yes he’s a complete moron, and anyone could have won that prize right? Certainly seems that everyone in this thread could have done it.

                I’m just saying that if he’s smart enough do that, when no one else did, then I choose to believe he was asking a more specific question about if there’s any fine-tuned LLMs specifically for ETL, and less about “durr what is ai? <drool>”

                Yes, even if he wants to use this magic LLM to speed run the US in to fascism to get a headpat from Papa Elon, it does not mean he drools over his keyboard, can’t figure out a microwave, and has no concepts of what’s LLMs are (despite, you know, creating his own custom ml models for fun…) I can hate him and what he’s doing and still be factual about his real accomplishments.

      • wise_pancake@lemmy.ca
        1·
        1 day ago

        I guess it’s just a dumb tweet question then. In not directly in the field and even I’m up to date in latest model benchmarks for tasks I need to do.

        I don’t know anything about this kid other than the tweet and Elon likes him.

  • sabreW4K3@lazysoci.al
    128·
    1 day ago

    I mean he’s not wrong.

    Edit: it seems the joke that LLMs just take other people’s data and regurgitates it in another format went over everyone’s head 🥺

    • lemmyng@lemmy.caEnglish
      80·
      1 day ago

      Using LLM for format conversion is like taking a picture of an electronic document, taking the card out of the camera and plugging it into a computer, printing the screenshots, taking those prints to a scanner with OCR, turning the result into an audio recording, and then dictating it too an army of 3 million monkeys with typewriters.

      • gsfraley@lemmy.world
        19·
        1 day ago

        Haha considering just how much irrelevant third-party training data you’d be looping into a format conversion, this metaphor really is spot-on.

      • htrayl@lemmy.world
        5·
        1 day ago

        Im not so sure. I think this is more of a question about taking arbitrary, undefined, or highly variable unstructured data and transforming it into a close approximation for structured data.

        Yes, the pipeline will include additional steps beyond “LLM do the thing”, but there are plenty of tools that seek to do this with LLM assistance.

      • MajorHavoc@programming.dev
        2·
        1 day ago

        So…my process (which you just accurately described) could be replaced by an LLM, after all? Hooray! Monkey feed isn’t too expensive, but a million mouths is still a million mouths.