Reflecting on WikiTok

(aizk.sh)

144 points | by aizk 16 hours ago

10 comments

  • Jdfmiller 12 hours ago
    This:

      And with regards to AI taking jobs - it obviously will become a serious problem in future. But being a doomer right now is like lying down in a parking lot waiting to get run over - you're surrendering to a pointless outcome while the rest of the world keeps moving.
    
    Great sentiment. I've had a similar experience with LLMs and writing code - helpful when keeping the requests small, and a background in the area is essential for knowing what is and isn't total crap. Feel the fear and do it anyway.

    Inspiring to see you take on a different career path and go for it, I feel i'm on a similar journey right now, thanks for taking the time to write it up.

    • throwawayk7h 4 hours ago
      This is not what a doomer is. A doomer is not a nihilist. A doomer is someone who recognizes a great threat of impending doom. They may raise the alarm bell in response. If they choose to lie down and wait to get run over, that's a nihilist doomer.
      • MarcelOlsz 2 hours ago
        Laying down and rotting is it's own thing entirely and the Doomers and the Rotters are at odds.
    • johnisgood 8 hours ago
      > and a background in the area is essential

      Yes, precisely. Maybe one could (re)make something using LLMs without understanding a thing, but that is as good as copy pasting from SO without understanding.

      • vondur 4 hours ago
        > but that is as good as copy pasting from SO without understanding.

        I'm sure there are a large amount of programmers who do this quite often..

        • johnisgood 2 hours ago
          Of course, they now probably switched to LLMs.
  • lwansbrough 12 hours ago
    > I built wikitok.io in about 2 hours (but not the iphone app that doesn't work, nor the play store rip off, nor wikitok.net but I'm getting ahead of myself). It all came from this tweet.

    This phrasing seems to suggest they think they invented the idea of "TikTok but it's Wikipedia". I see the author is OP, so my suggestion might be to consider rephrasing a bit as it comes off a bit accusatory.

    I did try my hand on this project after seeing this bare-bones viral version. (I had the same idea in my notes app dated a couple years ago.) I went a different route, opting to pre-parse wikitext via my own API to deliver the app an AST that can be rendered natively & prettier than your standard Wikipedia page. Not a fun format to parse. Not fun at all. I don't recommend it. And it took significantly longer than 2 hours and was never released, so props to the author for turning this project around so fast.

    • diggan 10 hours ago
      > This phrasing seems to suggest they think they invented the idea of "TikTok but it's Wikipedia". I see the author is OP, so my suggestion might be to consider rephrasing a bit as it comes off a bit accusatory.

      Am I missing something, it comes off as the precise opposite to me? OP wrote "I built X, but the idea came from this source" basically, acknowledging they built the thing but the idea came from somewhere else.

      • aizk 9 hours ago
        Some of them came before me, but most of them were clones that came after me. I just wanted to highlight what happens when you go viral - there will be copycats.
    • aizk 9 hours ago
      The point of that phrase was just to highlight the derivatives the I had no affiliation with.

      I built it and marketed it, but the idea came from some tweets that were gaining momentum.

      • lwansbrough 5 hours ago
        Oh I see. My apologies, my assumption was that you had wrote the tweet.
        • aizk 3 hours ago
          Maybe I should've made that a screenshot or embedded tweet, if you scroll over it / don't click on it you lose context. Realtime website UI feedback here.
    • slevis 10 hours ago
      > This phrasing seems to suggest they think they invented the idea of "TikTok but it's Wikipedia".

      The author is giving credit. Literally the opposite of your interpretation.

      > I had the same idea in my notes app dated a couple years ago.

      On the other hand this seems as if you now want to claim to be the inventor of the idea?

      • aizk 9 hours ago
        A mixture of both. Some of those were copycats and some of those came before me, (the iPhone app, but I didn't know about it when I made the website). The point I was making was there's lots of clones happening when you go viral.
    • Emma_Goldman 3 hours ago
      Bizarre confabulation: the text you quote says nothing of the sort. They say the made one site, not to be confused with other, similar sites, and that the idea originates with someone else's tweet. Why jump to negative conclusions when they are sharing their project for the first time?
  • timkq 13 hours ago
    It's great that LLMs provide opportunity for non-software engineers to make tech products, but I wonder how those "vibe-coded" products will fare when faced with actually maintaining the code (and also accounting for tech debt..)
    • mrkramer 1 minute ago
      Tech debt of your hobby pet project? It's not like millions of people will be using it.
    • pajamasam 12 hours ago
      It's not like we're doing very well with maintenance and tech debt in any case. AI might be able to help with that in the future.
      • blueflow 11 hours ago
        Look at your tech stack, go down until you come to the level where things "just work". This is where the maintained software begins. The stuff you fill your docker base images with.
    • diggan 10 hours ago
      > faced with actually maintaining the code (and also accounting for tech debt..)

      I guess they'll learn it as they come across it? "Oh Claude, my code is almost like a plate of spaghetti, how can I make it easier to add new features without breaking something else?" "Dear user, here is what technical debt and unit tests mean: ..."

      Besides, all of us self-learned programmers mostly learned about those things the hard way as well, by experiencing the real drawbacks of not caring about such things until too late and stuff is already up and running with real users.

      • ryukoposting 9 hours ago
        Here's the thing: the formally trained programmers learn it that way too. They're just less inclined to admit it.
    • aizk 5 hours ago
      Does writing software with an LLM not make me a software engineer?
    • non- 4 hours ago
      OP is a software engineer, so this is a software engineer using LLM's to make tech products.
    • Onavo 12 hours ago
      But OP is a software engineer, I doubt a non software engineer can turn around a vibe coded app so quickly.
      • aizk 3 hours ago
        Feel free to judge for yourself what I am. Started in civil engineering, pivoted hard 6 months ago. That gave me a leg up in UI/UX, design experience, all that.

        https://www.aizk.sh/Isaac's%20Resume.pdf

        Also vibe coding is useless without marketing skills, deployment skills, distribution, social media skills, etc.

  • the-chitmonger 4 hours ago
    Hey, I'm also a former civil engineer-turned SWE in the NJ/NYC area! Nice to know that there are more of us out there. I already spend hours looking through Wikipedia articles, so when your site dropped I was on it right away. I dodged the AI conversation entirely by getting into a state government position where my job is all but guaranteed by the union.
  • wonger_ 13 hours ago
    I feel like I could easily be caught by one of those journalist scams. Especially when low on sleep.
  • janalsncm 4 hours ago
    Disagree on the “algorithm” bit but that’s ok.

    “Random” is an algorithm. It just says that the next article you should read has no relationship with anything you’ve read before. That is a point of view. It’s good for an “explore” phase, where you want to expose yourself to as much variety as possible.

    But eventually most people want to “exploit” their impressions from before. Just like I don’t want to always roll the dice on restaurants, sometimes I want to go back to one that I know is good.

  • wewewedxfgdf 13 hours ago
    There's no date on the article so its hard to know when its from.
  • pajamasam 12 hours ago
    I like this point of view:

    > And with regards to AI taking jobs - it obviously will become a serious problem in future. But being a doomer right now is like lying down in a parking lot waiting to get run over - you're surrendering to a pointless outcome while the rest of the world keeps moving. There's still so much to build and accomplish.

  • bradleykingz 4 hours ago
    It's shocking how unhinged scammers can be... Unstoppable farting dog? Seriously...?
  • dev_chhatbar 9 hours ago
    I really like this idea! Thank you for making it! I personally prefer web-apps to phone-apps but wouldn't mind installing one if its in the pipeline from OP!
    • aizk 9 hours ago
      There is no phone app! There's a progressive web app you can download. Funnily, I thought I solved the mobile issue making the PWA until I realized 99% of people have no idea what a progressive web app is.
      • tonyhart7 9 hours ago
        "I realized 99% of people have no idea what a progressive web app."

        I never used it, Yeah I know it exist but who tf use that???? and I'm considering myself "techy"

        • aizk 9 hours ago
          Yeah I had a request on GitHub for it, so I implemented it! But it was only a "fix" for a very specific technical group people, not ALL the users. Good lesson learned there.
          • non- 4 hours ago
            Maybe a "Download App" button that installs the PWA would help
            • aizk 2 hours ago
              That smart but not ideal - think of the people who will navigate directly to the app store and type "wikitok"