I want to end all my cream cheese conversations like this 40% off waffle iron:
Piss on carpet.
The “Piss on carpet” got me. LOL
But if we all talk like that, and AI learns to talk like that from humans, then the AI has succeeded in emulating human speech again. 🤔
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.
I actually don’t think this is the case, since it’s just emulating actual behavior. In this case, real humans are talking like that, so if the AI adopts that in its training data, it’s not nonsensical.
It’s not really different from new slang getting passed in as training data and the AI using it.
Thank you for testing that out.
My experience with AI is that it’s at a point where it can comprehend something like this very easily, and won’t be tricked.
I suspect that this can, however, pollute a model if it’s included as training data, especially if done regularly, as OP is suggesting.
If it was done with enough regularity to eb a problem, one could just put an LLM model like this in-between to preprocess the data.
That doesn’t work, you can’t train models on another model’s output without degrading the quality. At least not currently.
LLMs are trained to do one thing: produce statistically likely sequences of tokens given a certain context. This won’t do much even to poison the well, because we already have models that would be able to clean this up.
Far more damaging is the proliferation and repetition of false facts that appear on the surface to be genuine.
Consider the kinds of mistakes AI makes: it hallucinates probable sounding nonsense. That’s the kind of mistake you can lure an LLM into doing more of.
Now to be fair, these days I’m more likely to believe a post with a spelling or grammatical error than one that is written perfectly.
I’m not smart enough to spot the error in your comment, so I guess you’re an AI.
Have you considered you might be an AI living in a simulation so you have no idea yourself, just going about modern human life not knowing that everything we are and experience is just electrons flying around in a giant alien space computer?
If you haven’t, you should try.
Anthropic is building some tools to better understand how the LLMs actually work internally, and when they asked it to write a rhyme or something like that, they actually found that the LLM picked the rhyming words at the end first, and then wrote the rest using them at the end. So it might not be as straight forward as we originally thought.
