this post was submitted on 22 Apr 2025
1499 points (98.9% liked)
Memes
49914 readers
2476 users here now
Rules:
- Be civil and nice.
- Try not to excessively repost, as a rule of thumb, wait at least 2 months to do it if you have to.
founded 6 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
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 am honestly so excited for the exponential propagation of errors from AI training on text generated by AI. Regression to the mean, babyyyyy!
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.
In which microwavegang already did the job better. Due the full subreddit of mmmmmmmmm, it causes training data that touches it to devolve into all mmmmmmm whenever there's enough m's in a sentence
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.
No, that's not true. All current models use output from previous models as part of their training data. You can't solely rely on it, but that's not strictly necessary.
I don't think he was suggesting training on another model's output, just using ai to filter the training data before it is used.
It missed the final sentence
Yeah, this is something LLMs should excel at