Skip Navigation

Posts
8
Comments
1848
Joined
2 yr. ago

  • Deleted

    Permanently Deleted

    Jump
  • People personifying and emotionally attaching themselves to a virtual avatar without a human voice is a slippery slope to LLM love.

    [[citation needed]]

    people are not stupid. there is a difference between Zentreya and ELIZA.

  • Deleted

    Permanently Deleted

    Jump
  • wait are you saying that people using text-to-speech online is a slippery slope to falling in love with an llm? wtf?

  • you should probably also check out beaker browser then, it's also trying to blur the line.

    personally i don't know if there is an actual benefit. most people seem content not producing things in fields they're not interested in. we'll never be able to get everyone on board with making websites no matter how simple the interface, just like we'll never be able to get everyone on board with gardening or carpentry. if you want to do it, you will learn. if you don't the learning curve is not the problem.

  • An oldie

    Jump
  • it's in adelaide, australia?

  • i'm no longer sure if you're envisioning a web browser or a website builder. your terminology is all over the place.

    and no, the semantic web is in no way an an open, global codebase. it's just a way of structuring html. i know berners-lee wanted the web to be more like what you are describing but the web we have today is not that. you'd need a new protocol.

  • there is a rich history of programming languages which are supposed to read like natural language. it gave us beauties like COBOL, SQL, and HyperCard. in other words, it's not good.

    as for text browsers, nyxt is probably the one that's closest, or some browser mode in emacs.

    ultimately what you want with navigation is precision and minimal typing, so a natural language interface is slow, and an ACE interface would be even slower.

  • no this makes sense, as long as you figure out that it's not actually about llms at all. they are just used as an example of what interaction would look like.

  • interesting idea. there are already text-based browsers like qutebrowser but they require mastering a command language. creating a natural language interface based on a constrained language is bound to come with the same sort of problem apple had with hypercard: easy to read, diabolic to write. i wonder how they solve for that.

  • jd would puke himself inside out if he went to germany

  • this is vx-adjacent i feel. really should set up a community for that.

  • so how do you choose which humans to experiment on? bearing in mind that any sort of incentive will automatically select for a particular subset, and randomness will "obviously" need to exclude a particular subset

  • "Sad Story 😥" - 2020 Twitter meme, has my previous comment as a line in it.

  • yeah that's what i don't really understand. they're like building a separate layer on top of git, when things like fossil exist.

  • who do you think gave you the skin

  • sorry you had to find out this way

  • this is bound to generate good faith arguments and rational discussion.

  • it's called ssh

  • ...git is federated. i'm assuming they're talking about things like issues and runners, but i don't think that's really necessary...

  • i am still rooting for patch requests to become more mainstream, it seems like the best possible solution. it just needs some discoverability.