• 1 Post
  • 134 Comments
Joined 2 years ago
cake
Cake day: July 4th, 2023

help-circle

  • 18107@aussie.zonetohomeassistant@lemmy.worldAdvices regarding AI prompt
    link
    fedilink
    English
    arrow-up
    2
    arrow-down
    1
    ·
    2 days ago

    I don’t believe any AI has the ability to do what you’re asking. AI often fails at the simplest of programming tasks, and even when the output runs, it usually has some major flaws.

    Even if the AI could do what you want, it would take more effort to find the right prompt than to just do the work, and the prompt would be longer than the resulting YAML code.

    You can ask for advice on specific home assistant features, or offer to hire someone to build the interface for you.

    My personal recommendation is to just give it a try. Make a few interfaces and automations, and try downloading and modifying other publicly accessible interfaces and automations until you’re happy with them. The YAML code makes it easy to copy other people’s work, and the non-YAML UI makes it relatively easy to try things without programming knowledge.




  • The aviation industry has a mental health crisis. Pilots are (rightfully) so scared of losing their jobs that they won’t seek the help that would make them safer pilots.

    No human will ever be perfect, and unfortunately the aviation industry doesn’t account for this when dealing with short periods of reduced mental health. Any pilot deemed unsafe to fly may never get their licence back again, even if the situation causing their mental health issues is gone.

    Mentour Pilot has a video about this specific incident where he highlights these specific issues. Xyla Foxlin has made a video about a different incident that highlights the same issues from a different perspective.

    Just as Crew Resource Management has saved many lives since it was introduced, a new mental health management system is needed to assist, not punish, pilots who are going through tough times.








  • Something similar to the way files (and bank transaction records) are modified on a drive. A first message indicating that a specific transaction is starting, a second message with the transaction, and a third message indicating the transaction is complete.

    If any message is not acknowledged, it can be resent (with an ID so it’s recognized as a duplicate), and if all else fails, flag a human.

    The system doesn’t need to be 100% accurate, just good enough that only a few humans are needed to fix the problems.

    The Byzantine Generals problem is only a problem if you need 100% certainty from both sides. If you’re willing to put up with 99.99% certainty, then network engineers have solved this problem many years ago.






  • Clippy never sold your data or demanded a subscription fee for something you already bought. Clippy just tried to help.

    The clippy movement is not about clippy as a program, but as an idea that companies need to be held accountable, and that we will hold them accountable.
    If a company tries to make a feature a paid subscription after you paid for the product, or releases and update that removes your privacy, we will be watching and we will hold them accountable.

    Companies can lie to one person or hide changes from a few people, but they can’t handle all of us. Samsung has already reversed their added subscription fee for a smart TV as a result of community action.