• 61 Posts
  • 1.94K Comments
Joined 1 year ago
cake
Cake day: June 24th, 2023

help-circle















  • Sort of, but not really.

    In basic terms, if an LLM’s training data has:

    Bob is 21 years old.

    Bob is 32 years old.

    Then when it tries to predict the next word after “Bob is”, it would pick 21 or 32 assuming somehow the weights were perfectly equal between the two (weight being based on how many times it occurred in training data around other words).

    If the user has memories turned on, it’s sort of like providing additional training data. So if in previous prompts you said:

    I am Bob.

    I am 43 years old.

    The system will parse that and use it with a higher weight, sort of like custom training the model. This is not exactly how it works, because training is much more in-depth, it’s more of a layer on top of the training, but hopefully gives you an idea.

    The catch is it’s still not reliable, as the other words in your prompt may still lead the LLM to predict a word from it’s original training data. Tuning the weights is not a one-size fits all endeavor. What works for:

    How old am I?

    May not work for:

    What age is Bob?

    For instance.





  • Is that still the case?

    This level of integration means that group VoIP in Matrix finally benefits from all of Matrix’s native end-to-end encryption, cryptographic identity and decentralisation - no longer handing over to a third-party system such as Jitsi which doesn’t integrate with Matrix’s encryption guarantees.

    And, native E2EE for voice and video (through the Element Call integration mentioned above) ensures that Matrix’s encryption guarantees now extend to video conferencing.

    Though I’m assuming you mean protocols not app names.