• 1 Post
  • 213 Comments
Joined 2 years ago
Cake day: June 7th, 2023
  • saigot@lemmy.catoTechnology@beehaw.org•Firefox could be doomed without Google search deal, says executive
    2·
    9 days ago

    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.catoMemes@lemmy.ml•AI will never be able to write like me.
    462·
    23 days 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.

  • saigot@lemmy.catoGaming@lemmy.ml•Nintendo Switch 2 Revealed.
    17·
    4 months ago

    My switch 1 is gathering dust, mostly because of the awful controllers. Looks like they made the controllers bigger, and the magnetic slide looks much better than the switch1. I hope they significantly reduced the stick drift problem. I hope they allow 3rd party controllers to turn on the device.

  • saigot@lemmy.catoTechnology@beehaw.org•Look Ma, No Batteries! Hands On With Lenovo's Self-Charging Keyboard
    2·
    4 months ago

    Where are you getting that number? There are many different types of supercapacitors, which vary in lifespan quite a bit, the conditions (mostly voltage and temp) also have a big impact. The article doesn’t specify the type of cap used.

    For instance this paper tests a supercapacitor rated for 2.7V at 2.5 and 3v. At 2.5v the cap is estimated to have a lifespan of 100yrs, with 3v scenario it’s 10.

    Keyboards don’t get very hot, and the voltage draw is very predictable so I don’t think designing a long lasting capacitor for this usecase is particularly tricky.

    I would be worried about the lifespan of the solar panel, but at least it’s still usable without that.