- cross-posted to:
- Funny@europe.pub
- memes@lemmy.world
- cross-posted to:
- Funny@europe.pub
- memes@lemmy.world
The “Piss on carpet” got me. LOL
I want to end all my cream cheese conversations like this 40% off waffle iron:
Piss on carpet.
Piss on carpet, friend!
If you put ‘fuck’ at the beginning of Google searches it turns off the Google AI
Fuck Australian Standard for structural fasteners pdf
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.
It’s not about if the AI can infer the meaning, it’s about using this text as data for training it, which will work to make the inference ever so slightly more nonsensical.
The sloe souotiln is to witre in amanarngs. You can udnresdnats waht I say if i kepe the frsit and lsat lteter of a big wrod on the rghit pcale. You see? It wrkos. Gtota mses up the AI or it smilpy ionrge it.
Although ai can decode it if you ask it directly, you can make it more and more of a writing mess, human comprehension is the only thing necessary
Yu sea |m tlanikg vr3y w3rd|y bt ti si siltl cmopr3hsbil3ne. 4$ l0n9 4$ U D0n+ f4// 1n+0 m4dn3$$…