• 4 Posts
  • 16 Comments
Joined 1 year ago
cake
Cake day: June 12th, 2023

help-circle
  • Wonder how the survey was sent out and whether that affected sampling.

    Regardless, with -3-4k responses, that’s disappointing, if not concerning.

    I only have a more personal sense for Lemmy. Do you have a source for Lemmy gender diversity?

    Anyway, what do you think are the underlying issues? And what would be some suggestions to the community to address them?









  • inspxtr@lemmy.worldtoSelfhosted@lemmy.worldForgejo v1.21 is available
    link
    fedilink
    English
    arrow-up
    4
    ·
    edit-2
    11 months ago

    yeah I guess maybe the formatting and the verbosity seems a bit annoying? Wonder what the alternatives solution could be to better engage people from mastodon, which is what this bot is trying to address.

    edit: just to be clear, I’m not affiliated with the bot or its creator. This is just my observation from multiple posts I see this bot comments on.



  • Thanks for the suggestions! I’m actually also looking into llamaindex for more conceptual comparison, though didn’t get to building an app yet.

    Any general suggestions for locally hosted LLM with llamaindex by the way? I’m also running into some issues with hallucination. I’m using Ollama with llama2-13b and bge-large-en-v1.5 embedding model.

    Anyway, aside from conceptual comparison, I’m also looking for more literal comparison, AFAIK, the choice of embedding model will affect how the similarity will be defined. Most of the current LLM embedding models are usually abstract and the similarity will be conceptual, like “I have 3 large dogs” and “There are three canine that I own” will probably be very similar. Do you know which choice of embedding model I should choose to have it more literal comparison?

    That aside, like you indicated, there are some issues. One of it involves length. I hope to find something that can build up to find similar paragraphs iteratively from similar sentences. I can take a stab at coding it up but was just wondering if there are some similar frameworks out there already that I can model after.







  • this is an interesting story but for those who prefer to read, here the article linked in the video description:

    https://thefourth.media/apartments/

    I also ran this through smmry to summarize. Below is the result:

    The Apartments With No Entrance A shady land sale has left the residents of Sea Park Apartments locked in a decades-long land dispute, with no control over their own homes.

    These apartments are “Enclosed” in more ways than one: The original developer of the apartments sold the apartment’s carpark and common areas - which surround the apartment blocks - to an individual, leaving residents in the unusual position of having their homes completely encircled by someone else’s private land.

    Built in the 70s and completed in the early 80s, Sea Park Apartments is one of the earliest apartments in Petaling Jaya, if not the earliest, constructed at a time when most residential developments in the area still involved landed properties.

    This meant residents had no way to access their homes without first trespassing on private property, and no control over the common facilities sited on that private land.

    The individual who purchased the disputed lands is Yap Say Tee, who once managed a hotel owned by the developer, and was earlier approached by the developer to manage the car park at Sea Park Apartments.

    With the developer’s sale of these lands to Yap, the rules of the game changed: The developer is no longer the registered owner of the disputed lands nor responsible for addressing the remonstrations of the residents, which reached a peak in 2013.

    With the facilities on private land, access road on private land, the property value will go down, and residents will have no agency.