• 3 Posts
  • 103 Comments
Joined 3 years ago
cake
Cake day: March 15th, 2023

help-circle

  • I don’t think it’s ADD. There’s a book called ‘thinking fast and slow’. In that book the psychologist separates the mind functions into two systems. System 1 is for intuition, no effort, fast thinking. System 2 needs effort, slow, but precise. What happens here is that simply people are trying to be efficient with their thinking and they use less system 2 which is required for reading.





  • The concept of understanding implies some form of meta-knowledge about the subject.

    That can be solved if you teach it the meta-knowledge with intermediary steps, for example:

    prompt: 34*3=
    
    step1: 4*3 + 30*3 = 
    step2: 12 + 10*3*3 = 
    step3: 12 + 10*9=
    step4: 12 + 90 =
    step5: 100 + 2 =
    step6: 102
    
    result: 102
    

    It’s hard to find such learning data though, but e.g. claude already uses intermediary steps. It preprocesses your input multiple times. It writes code, runs code to process your input, and that’s still not the final response. Unfortunately, it’s already smarter than some junior developers, and its consequence is worrying.


  • But LLMs are not simply probabilistic machines. They are neural nets. For sure, they haven’t seen the world. They didn’t learn the way we learn. What they mean by a caterpillar is just a vector. For humans, that’s a 3D, colorful, soft object with some traits.

    You can’t expect that a being that sees chars and produces chars knows what we mean by a caterpillar. Their job is to figure out the next char. But you could expect them to understand some grammar rules. Although, we can’t expect them to explain the grammar.

    For another example, I wrote a simple neural net, and with 6 neurons it could learn XOR. I think we can say that it understands XOR. Can’t we? Or would you say then that an XOR gate understands XOR better? I would not use the word understand for something that cannot learn. But why wouldn’t we use it for a NN?




  • What I meant is that you cannot turn any existing webpages to a basic page with some simple tricks like disabling js. That would be a never-ending fight.

    You are the one adding extra complexity

    I’m not the one defining the business requirement. I could build a site with true progressive enhancement. It’s just extra work, because the requirement is a modern page with actions, modals, notifications, etc.

    There are two ways I can fulfill this. SSR with scripts that feel like hacks. Or CSR. I choose CSR, but then progressive enhancement is now an extra work.








  • Who said making unbloated pages impossible? Your comment would be more serious without your emotions.

    Source code is the source code which gets transformed to some target code. An obfuscated code is not source code.

    A reminder, in the past, large pages downloaded all stuff at once. In contrast, with dynamic imports the first load is much much faster. And that matters most. And any changes in dynamic content would just require the dynamic data to be downloaded. My phone lasts at least 2 days with one charge (avg usage), but I charge it every night, that’s not an issue.



  • As a web developer, I see js as a quality improvement. No page reloads, nice smooth ui. Luckily, PHP times has ended, but even in the PHP era disabling jQuery could cause problems.

    We could generate static html pages It just adds complexity.

    Personally I use only client-side rendering, and I think, that’s the best from dev perspective. Easy setup, no magic, nice ui. And that results in blank page when you disable js.

    If your motivation is to stop tracking.

    • replace all foreign domain sources to file uris. e.g.: load google fonts from local cache.
    • disable all foreign script files unless it’s valid like js packages from public CDNs, which case load them from local cache.

    If your motivation is to see old html pages, with minimal style, well it’s impossible to do them reliably. If you are worried about closed-source js. You shouldn’t be. It’s an isolated environment. if something is possible for js and you want to limit its capability, contribute to browsers. That’s the clear path.

    I can be convinced. What’s your motivation?