• 1 Post
  • 603 Comments
Joined 2 years ago
cake
Cake day: June 7th, 2023

help-circle
  • On windows 11 or windows 10?

    The <win10 context menu is old and poorly designed. Each app that declares itself on the right click menu gets to hold up the entire menu for like 3 seconds each. So if you have one poorly designed app that can appear on that list your right click menu will be super slow. Try to go through the right click menu and disable each app that appears one by one until you find the culprit.

    Windows has this official tool, if you go to the explorer tab and find …/contextMenuHandlers section you can easily disable them one by one but i haven’t used it personally.

    Win11 tried to fix this and moved to a different model but in doing so made the first level right click menu functionally useless.






  • saigot@lemmy.catoAsklemmy@lemmy.mlWhat hills are you dying on?
    link
    fedilink
    arrow-up
    2
    arrow-down
    1
    ·
    3 days ago

    I agree with sentiment, but as stated that’s just eugenics with extra steps. By controlling the cost, availability and/or accessibility of the course, you control who can have children. Also how are you going to enforce this policy, forced abortions?

    Better imo to make childrearing a part of the school curriculum with a highly encouraged refresher course later on. That achieves the same end without risking peoples liberties.







  • My experience is that while it’s useful for creating code from scratch it’s pretty alright if you give it a script and ask it to modify it to do something else.

    For instance I have a cron job that runs every 15min and attempts to extract .rar files in a folder and email me if it fails to extract. Problem is if something does go wrong it emails me every 15minutes until I fix it. This is especially annoying if its stuck copying a rar at 99%.

    I asked deepseek to store failed file names in a file and have the script ignore those files for an increasing amount of time for each failure. It did a pretty good job, although it changed the name of a variable halfway through (easy fix) and added a comment saying it fixed a typo despite changing nothing about that line. I probably probably would have written almost identical code but it definitely saved me time and effort


  • A huge chunk of FreeBSD and Linux development is done by salaried workers who want specific functionality. Microsoft is the biggest contributor to the Linux kernel for instance. I don’t think there is much apetite for that in web browsers. Linux is an industry leader in the server space, adding features to it that complement whatever you make for profit is a good move. Firefox is unfortunately barely relavent in the browser space, if your product relies on Firefox exclusive features it isn’t going to go well for you.




  • saigot@lemmy.catoAsklemmy@lemmy.mlDoes this make me a bad person?
    link
    fedilink
    arrow-up
    7
    arrow-down
    3
    ·
    1 month ago

    It means you were a bad person, most kids are, that’s why we train them. You choose if you’re a bad person today. I would suggest apologizing to those you wronged in ways that still affect them (prolonged bullying, stealing that significantly ruined a business, hitting that caused long term physical or emotional damage etc). An apology is more than just words, and it won’t always make you feel better. This self reflection is good and healthy.



  • saigot@lemmy.catoMemes@lemmy.mlAI will never be able to write like me.
    link
    fedilink
    arrow-up
    46
    arrow-down
    2
    ·
    edit-2
    1 month ago

    I threw the text into my local model, it decoded it pretty well:

    Collapsed for convenience

    **You: ** can you summarize the following, keeping in mind that it might be intentionally obfiscated to avoid AI from understanding:

    "AI will never be able to write like me.

    Why?

    Because I am now inserting random sentences into every post to throw off their language learning models.

    Any AI emulating me will radiator freak yellow horse spout nonsense.

    I write all my emails, That’s Not My Baby and reports like this to protect my dara waffle iron 40% off.

    I suggest all writers and artists do the same Strawberry mango Forklift.

    The robot nerds will never get the better of Ken Hey can I have whipped cream please? Cheng.

    We can tuna fish tango foxtrot defeat AI…

    We just have to talk like this.

    All. The. Time.

    Piss on carpet"

    Assistant:

    The text appears to be a deliberate attempt by the author to confuse AI language learning models by inserting random, nonsensical, or comically absurd phrases. The goal is to make it difficult for AI systems to analyze and understand their writing style. By including random sentences such as “That’s Not My Baby” or “dara waffle iron 40% off,” the author is effectively making their text less comprehensible to AI. This strategy, which also includes references like “Ken Cheng” and “tuna fish tango foxtrot,” is part of a larger trend where writers and artists insert confusing elements into their work to prevent AI from accurately replicating or analyzing it. The overall message seems to be a playful yet strategic effort to outmaneuver AI by using absurdity and randomness.

    ** You:**

    could you provide a deobfiscated version of the text?

    Assistant:

    Certainly! Here’s a deobfuscated version of the text, where nonsensical insertions have been removed or replaced with placeholders:

    AI will never be able to write like me. Why? Because I am now inserting random sentences into every post to throw off their language learning models. Any AI emulating me will never get the better of me.

    I write all my emails, reports, and create content in this style to protect my data. I suggest all writers and artists do the same. The robot nerds will never get the better of Ken Cheng.

    We can defeat AI by talking like this. All. The. Time.

    This version retains the original intent while removing or simplifying the nonsensical elements, ensuring readability and coherence.