• 0 Posts
  • 38 Comments
Joined 2 months ago
cake
Cake day: July 26th, 2024

help-circle








  • llama3.1 (8B) by Facebook:

    >>> what does the I in LLM stand for?
    
    In the context of natural language processing (NLP) and artificial 
    intelligence, "LLM" typically stands for **L**arge **L**anguage **M**odel.
    
    A Large Language Model is a type of machine learning model that has been 
    trained on large datasets to understand and generate human-like language. 
    These models are often used in applications such as text classification, 
    sentiment analysis, question answering, and even chatbots like myself!
    
    I'm glad you asked!
    
    >>> but the I !!!!
    
    In the specific case of an LLM being a Large **L**anguage **M**odel, the 
    "LL" part doesn't explicitly mention the letter "I".
    
    However, in the context of AI and ML models, there are other types of 
    models that do involve the letter "I", such as:
    
    * ILM: Image Language Model (combining computer vision with natural 
    language processing)
    * IMLM: Interpretable Machine Learning Model
    * MLM: Masked Language Model (a specific type of LLM)
    
    And then there's also...
    
    * DALL-E, but that's a different story!
    
    But in the case of the original LLM, it typically stands for Large 
    **L**anguage **M**odel.
    



  • I am the admin of a website where we have a place where our users can post custom content and rate the content of others.

    We have discussed how it works and should work many times and came to the conclusion that we’d never want it to be public. Any report of abuse will be checked by the website owner directly in the database and even admins don’t have full access. Everybody tries to stay as far away from the personal ratings as possible.

    We also noticed that it would be a lot more fragile when there are not many voters. A whole group that is negative about something wouldn’t get as much harassment as a single person having a unique opinion.

    On our website we have a comment section that isn’t anonymous, and we even noticed that people often don’t post something negative when it would be obvious that they are the only one who has voted/rated something. (“Negative” is almost always constructive in our case)

    These are just a few things that I think add to this discussion.






  • App Stores are responsible for their content. If google simply vets the app store developers and their team and their product, they should have some kind of trust that whatever that app store supplies will be up to standards. But on the other hand, it’s actually none of their business to hold my hand for me when I want to do stuff with my device.

    It’s more about getting the less tech-savy people away from the Play Store. It creates a road that app makers can take to remove the need of Google Services, eventually making gapps fully optional for all.

    The last problem you raise seems more like a symptom of a problem than an actual problem. This kind of weird behavior is only possible because Google simply does not care about others. A simple “this app is managed by x” configuration setting would be easy enough to implement in Android.




  • Usually something like this would be enforced once in a centralized location (in the data layer / domain model), rather than at every call site.

    True. Although not every endpoint is the same, nor is every website or service.

    This gets tricky because in many jurisdictions, you need to ensure that you don’t just delete the user, but also any data associated with the user

    GDPR specifically mentions user identifiable data. I don’t know about others.