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.
- 0 Posts
- 136 Comments
Joined 2 years ago
Cake day: June 7th, 2023
You are not logged in. If you use a Fediverse account that is able to follow users, you can follow this user.
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.
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.
I Wonder if that could be a somewhat mutually acceptable anticheat solution. Launch any competitive game in a custom image that is locked down.
deleted by creator
TheFatRat - Xenogenesis
And just because people keep hammering screws doesn’t mean hammers aren’t useful.
1·1 month agoYeah and no one federates with them for a reason, despite the fact it would about 500x the userbase.
Corporate buy in, just look at bluesky. I don’t want lemmy to grow.
Just like a curt “yes” or even “yes sir” can be seen as somewhat rude in some contexts, so to can its emoji equivalent.
What did they do this time or is this still the paid subreddit wave?
The only time I would use seasons would be in a weather related way. When i say “I ski in the winter, and run in the summer” you don’t need to know whether i ski in July or December, you just need to know I ski when it’s cold.
For several years my pc would only turn on while at a 45degree angle, not on its side and not upright but tilted 45degrees. After it turned on I could put it back and it’d be fine.
Eventually I moved and the pc ended up upside down and shaken, I put it down and a screw fell out of the psu. Problem solved!
Not everyone who is deeply religious is a true believer. Some just see it as a community, and the rigid adherance to the rules as the key to that community. One of the rules is to always say you’re a true believer, though. My sister in law is like this. She just decided one day to join a religion, researched the ones with the perks that best suited her and joined it.
I use boost, I like it’s swipe view. It’s mostly just what I was using with reddit and there’s no reason to switch.
Seeing ok go with my future wife is one of my all time favourite memories.
I almost always skip the last 3 steps of my stairs on the way down.
add t0, t1, t2is way easier for humans than the0x014B4820that it could be assembled into, and what programmers had to use before assembly existed.
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