• 0 Posts
  • 8 Comments
Joined 3 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.



  • Yeah, but the astroturfing botfarms are only activated to foment “oohh aahh yeah gotta be responsible with our children’s debt” opinions when it’s the other way around. And of course all big “news” entertainment papers and shows are in on it because of access and money. I mean, they’re all doing what they’re paid for and the general public can’t be arsed to be smart about it, call bullshit and cut off the value extraction because of perceived inconveniences (data harvesting = ability to manipulate/steer public opinion = value to sell to those seeking power & control). the populace is the commodity being sold here.

    We are all cooked