• 0 Posts
  • 25 Comments
Joined 2 years ago
cake
Cake day: July 1st, 2023

help-circle
  • Hmm. I had pretty much the same experience, and wondered about having multiple conversation agents for specific tasks - but didn’t get around to trying that out. Currently, I am using it without LLM, albeit with GPU accelerated whisper (and other custom CV tasks for camera feeds). This gives me fairly accurate STT, and I have defined a plethora of variable sentences for hassil (intent matcher), so I often get the correct match. There is the option for optional words and or-alternatives, for instance:

    sentences:
     - (start|begin|fire) [the] [one] vaccum clean(er|ing) [robot] [session]
    

    So this would match “start vacuum”, but also “fire one vacuum cleaning session”

    Of course, this is substantial effort initially, but once configured and debugged (punctuation is poison!) works pretty well. As an aside, using the atom echo satellites gave me a lot of errors, simply because the microphones are bad. With a better quality satellite device (the voice preview) the success rate is much higher, almost flawless.

    That all said, if you find a better intent matcher or another solution, please do report back as I am very interested in an easier solution that does not require me to think of all possible sentence ahead of time.





  • It would seem like that when reading news, but it’s really not that bad. Enshittification is an issue though, but mostly being driven by the us oligarchs worldwide. A lot of the outrage/opinion manufacturing “media-news” never becomes reality on the ground.

    The issue with nonsensical invasive surveillance tech is, logic and facts usually and eventually prevail, for instance backdooring systems for one group is backdooring for everyone, it just puts a huge target on your system and is ultimately ineffectual in its purpose, because the people of interest will adapt almost instantly (see examples “war on drugs”, “ending piracy”). In the end it is a losing battle, akin to trying to legislate wind to blow only in one direction.








  • Well, it’s a bit better than that, simply because you can train AI with solar power. Probably nobody does that currently, as it’s easier, faster-to-market and probably (for whatever corrupt reason) cheaper for business to let it run on burning fossils/nuclear. Currently there’s an insane amount of waste, often 1000s of models are trained and only the best performing one is deployed - and then it’s just a fancy autocomplete. The better use is for prediction of material failure, new medicine and protein folding, generally improved processes.

    With asbestos you get some convenience, but it’ll be for eternity a pain to find a waste management facility that will accept it.