SemanticWebBrowser - A browser for the semantic web with a controlled natural language as the primary interface

Submitted ⁨⁨1⁩ ⁨week⁩ ago⁩ by ⁨blue_berry@lemmy.world⁩ to ⁨technology@lemmy.world⁩

https://github.com/user-attachments/files/21751119/Semantic.Web.Browser_2025_08_13_5.pdf

The fundamental idea of this paper is for ChatGPT-like apps to lose natural language for less energy consumption and more determinism in their answers based on controlled natural languages like ACE; for the user to be able to modify this trade-off-ratio at will based on LLMs (which is not possible when starting from a ChatGPT-like app); and to capture this new paradigm in a new type of browser that has natural language as its primary interface, here called a semantic web-first browser.

source

Comments

Sort:hotnew top

lime@feddit.nu ⁨1⁩ ⁨week⁩ ago
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.

source
- blue_berry@lemmy.world ⁨1⁩ ⁨week⁩ ago
  
  there are already text-based browsers like qutebrowser hypercard Awesome! Thanks for the references, didn’t know there were already some applications in this direction
  
  source
  - lime@feddit.nu ⁨1⁩ ⁨week⁩ ago
    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.
    
    source
    -> View More Comments
db2@lemmy.world ⁨1⁩ ⁨week⁩ ago
This reads like someone played madlibs with an early draft sci fi show script.

source
- lime@feddit.nu ⁨1⁩ ⁨week⁩ ago
  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.
  
  source
- thisbenzingring@lemmy.sdf.org ⁨1⁩ ⁨week⁩ ago
  that or just total bullshit
  
  source
vacuumflower@lemmy.sdf.org ⁨1⁩ ⁨week⁩ ago
Seems weird, but there’s another application of these models that for me doesn’t - to convert, say, usual webpages into webpages with proper semantic markup or something like that. For readability and scraping and what not.

Possibly even to make “self-adjusting” gateways representing, say, a social network webpage as an XMPP service. Or to use PGP for private messages in them. Something like that.

Anyway. Until someone does something like that, and that takes enormous amounts of work and discipline, that’s just blabber.

source