Practical advice for dealing with AI rejection.

[ShelbyDawn57]

There have been countless threads on AI rejection over the past several months, and yet another today. As a group, we have offered and continue to offer a wide variety of suggestions to other authors fighting this dreaded demon. I'd like to see if we can consolidate some of this sage wisdom in a single thread that perhaps @Laurel and @Manu can pin to the top of this forum as an easy reference from those of us in the trenches on how to deal with the issue. I'll start with something I posted in this post a few weeks ago.

Please reply with your suggestions and let’s see what happens.

And please, let's not turn this into an argument over semantics. Let's try to keep it restricted to things that might actually help.

----

Some practical advice based on what has been working for me so far.... Other may disagree, but I have yet to see anyone answer this question with concrete examples, and no guarantees. My next story could get kicked back, too...

1. Vary your sentence length. Short is good. Sometimes, though, you need to go longer, espouse on what you're describing, dig into the feeling of the moment to get to the core of the character's motivation. Consistent sentence length is not only boring, it's what AI does, so don't do that. Got it?
2. Inject some personality, some emotion into your writing. "Tom hated his job and only stayed for the money." is flat, boring, mechanical. "The last fifteen minutes felt like hours as Tom watched the clock, waiting for five o'clock and his escape from the hellhole he called his job, cursing the bi-weekly check that shackled him to the tedium." says the same thing but paints a deeper picture of what Tom feels.
3. Use big words, or as @EmilyMiller might say, sesquipedalienate(is that a word?). View attachment 2591428Get creative with metaphors and other figures of speech. Use Similes and personification, hyperbole, irony, euphemisms. Throw in a pun or two. Add an oxymoron. AI doesn't do these things.
4. When it comes to grammar, use proper punctuation and spelling, but break all the other rules. Use. One. Word. Sentences. for emphasis, use dialect, y'all; do stuff like that. In dialog, remember people don't always talk in complete thoughts. Get creative with dialog tags, too.
   "Sometimes they, um, uh, you know, they, um, sort of, shit..." Derick shook his head, frustrated that the words just disappeared.
   "Lose track of what they're trying to say?" Emily chucked, showing her amusement at his discomfort.
   "Fuck you." He shook his head trying not to laugh with her.
   "Later." She winked.
   Notice none of my tags are "he said" or "she said" but you know exactly who is speaking.

You're writing a piece of fiction not a term paper or a business brief.
Bottom line, variety, creativity, use them. AI offers the median example of what it writes and only knows what it's told. Make it obvious through your words that you're not a robot, and you don't even have to click all the boxes with a bus in them.

 

[EmilyMiller]

@AwkwardlySet

 

[EmilyMiller]

Post in thread 'my story keeps getting flagged for AI, NEED HELP'
https://forum.literotica.com/thread...agged-for-ai-need-help.1648692/post-102249675

 

[AwkwardlySet]

Thanks for starting this, Shelby.

I think your post makes a solid core around which we can formulate all the advice we can give. I believe the guide should have an introduction where we would let the rejected authors know that this is a self-help guide based on our best guesses of how to solve their problem with AI rejection, and that there's no guarantee that their story will go through if they follow it.

In my opinion, the intro should also state that, while a good deal of the tips in the guide are what we believe to be good writing advice, some of it is mostly meant to avoid triggering the algorithm the website uses for AI detection. There are other legit writing styles, different from what we advise in the guide.

In the core, I'd add the advice to avoid the em-dash, as those are known triggers for detection algorithms.

I'd add the advice to avoid the rule of three. An example: "This guide is solid, helpful, and comprehensive."
The AI often writes sentences in such a way.

Maybe also add how AI often writes a rhetorical question and immediately answers it. And so on.

 

[EmilyMiller]

I'd add the advice to avoid the rule of three. An example: "This guide is solid, helpful, and comprehensive."
The AI often writes sentences in such a way.

My work is overbrimming with these and I’ve never had a problem.

 

[EmilyMiller]

Maybe also add how AI often writes a rhetorical question and immediately answers it. And so on.

Me? Write rhetorical questions? Nah!

 

[AwkwardlySet]

My work is overbrimming with these and I’ve never had a problem.

It's something I noted early on in the way AI writes. Maybe it doesn't trigger Laurel's algorithm, or maybe you have no other red flags in your stories, so the trifecta isn't enough. IDK. For me, it has always been a tell of AI-writing if it's abundantly present.

 

[ShelbyDawn57]

Post in thread 'my story keeps getting flagged for AI, NEED HELP'
https://forum.literotica.com/thread...agged-for-ai-need-help.1648692/post-102249675

Great minds and all that...

 

[PennyThompson]

I'm sorry and I don't want to turn this thread into an argument (it probably will become one with or without me) but I don't believe any of these writing style mechanics issues are at all responsible for whether a story is flagged as AI generated or not

 

[AwkwardlySet]

I'm sorry and I don't want to turn this thread into an argument (it probably will become one with or without me) but I don't believe any of these writing style mechanics issues are at all responsible for whether a story is flagged as AI generated or not

By all means, enlighten us then. What does lead to a story being flagged?

 

[EmilyMiller]

For me, it has always been a tell of AI-writing if it's abundantly present.

As it is in my work, indubitably, clearly, and without a shadow of doubt. Then AI doesn’t handle anal sex with any degree of verisimilitude

 

[MrPixel]

I'd add the advice to avoid the rule of three. An example: "This guide is solid, helpful, and comprehensive."

What? No Tom, Dick, or Harry? Manny, Moe, and Jack? Larry, Moe, and Shemp?

Pshaw!

 

[EmilyMiller]

Then AI doesn’t handle anal sex with any degree of verisimilitude

Speaking of AI and anal sex. I’m quite proud how restrained I was in The Story of Nix. The only anal sex in nearly 90,000 words was Nix’s ‘creator’ calibrating her response to it with a sensor-laden probe in the lab. She never got to use this particular skill set

 

[EmilyMiller]

What? No Tom, Dick, or Harry? Manny, Moe, and Jack? Larry, Moe, and Shemp?

Pshaw!

Rumi, Mira, and Zoey!

 

[BeechLeaf]

This would make an excellent Captcha: to prove you're human, derail the thread into a discussion of anal sex. I think we're onto something here.

 

[ShelbyDawn57]

 

[PennyThompson]

By all means, enlighten us then. What does lead to a story being flagged?

Using a tool or service that generates or modifies text using a large language model

From what I can tell, very nearly every single post about AI rejections that we see here are from people who have either:

• Used Grammarly or Quillbot or some other writing tool to "check their grammar," which turns out to mean they let those tools rewrite sentences and words for them
• Used translation software to translate from their home language into English
• Used Word's copilot writing tools to correct for grammar or other mechanical elements

People don't think of those tools as AI, but they are. Every single one of them now uses an LLM to function. Any time you let a tool modify your text, it's mechanically not any different from letting ChatGPT generate text for you.

And the part about it that sucks is that if you used one of these tools from the very beginning throughout your writing process, there's not really anything you can do to undo it, there's no "original" version that you can revert to.

So of course people get mad and frustrated about that, because the only answer we can give them is "write a new story from scratch and don't use tools."

 

[VallesMarineris]

There have been countless threads on AI rejection over the past several months, and yet another today. As a group, we have offered and continue to offer a wide variety of suggestions to other authors fighting this dreaded demon. I'd like to see if we can consolidate some of this sage wisdom in a single thread that perhaps @Laurel and @Manu can pin to the top of this forum as an easy reference from those of us in the trenches on how to deal with the issue. I'll start with something I posted in this post a few weeks ago.

Please reply with your suggestions and let’s see what happens.

And please, let's not turn this into an argument over semantics. Let's try to keep it restricted to things that might actually help.

----

Some practical advice based on what has been working for me so far.... Other may disagree, but I have yet to see anyone answer this question with concrete examples, and no guarantees. My next story could get kicked back, too...

1. Vary your sentence length. Short is good. Sometimes, though, you need to go longer, espouse on what you're describing, dig into the feeling of the moment to get to the core of the character's motivation. Consistent sentence length is not only boring, it's what AI does, so don't do that. Got it?
2. Inject some personality, some emotion into your writing. "Tom hated his job and only stayed for the money." is flat, boring, mechanical. "The last fifteen minutes felt like hours as Tom watched the clock, waiting for five o'clock and his escape from the hellhole he called his job, cursing the bi-weekly check that shackled him to the tedium." says the same thing but paints a deeper picture of what Tom feels.
3. Use big words, or as @EmilyMiller might say, sesquipedalienate(is that a word?). View attachment 2591428Get creative with metaphors and other figures of speech. Use Similes and personification, hyperbole, irony, euphemisms. Throw in a pun or two. Add an oxymoron. AI doesn't do these things.
4. When it comes to grammar, use proper punctuation and spelling, but break all the other rules. Use. One. Word. Sentences. for emphasis, use dialect, y'all; do stuff like that. In dialog, remember people don't always talk in complete thoughts. Get creative with dialog tags, too.
   "Sometimes they, um, uh, you know, they, um, sort of, shit..." Derick shook his head, frustrated that the words just disappeared.
   "Lose track of what they're trying to say?" Emily chucked, showing her amusement at his discomfort.
   "Fuck you." He shook his head trying not to laugh with her.
   "Later." She winked.
   Notice none of my tags are "he said" or "she said" but you know exactly who is speaking.

You're writing a piece of fiction not a term paper or a business brief.
Bottom line, variety, creativity, use them. AI offers the median example of what it writes and only knows what it's told. Make it obvious through your words that you're not a robot, and you don't even have to click all the boxes with a bus in them.

Another technique is to sprinkle your story with the seven words you can't say on TV: "shit", "piss", "fuck", "cunt", "cocksucker", "motherfucker", and "tits". This should not be difficult, given the genre this site specializes in.

I continue to be puzzled that "tits" makes the short list, but others such as "asshole", "bitch", and "dickhead" are not.

 

[ElectricBlue]

Speaking of AI and anal sex. I’m quite proud how restrained I was in The Story of Nix. The only anal sex in nearly 90,000 words was Nix’s ‘creator’ calibrating her response to it with a sensor-laden probe in the lab. She never got to use this particular skill set

Ages ago one of my beta readers gave me a quota for anal sex in my stories. I've heeded his advice every since, but it's still my only indulgence.

 

[BobbyBrandt]

As most of the suggestions imply, anyone faced with an AI rejection has few options other than to rework their story to eliminated any potential trigger elements mentioned here.

What might be helpful is for there to be a "Before you write: How to avoid AI rejections" piece that included most of this advice.

Once the story is written, the options for an author are frequently limited. Going back and trying to "strip out" any corrections made by an AI tool would be an exercise in futility for almost everyone. They could go through their story to make style changes as several have suggested here, but if the work is their true or natural style, any stylometric analysis would probably pick up on their attempted changes.

 

[BobbyBrandt]

From another thread on the subject:

A human editor will typically send your original manuscript back to you with notes on identified issues or suggestion for you to make yourself. They don't make those changes for you.

If you were to use an AI-assisted tool to identify suggested edits to your work in the same way, there would likely be no issues. Rejections occur when you allow the "editor" to make the changes on your behalf. Doing so makes the work not longer purely yours, exactly the same as if a human editor did so.

 

[EmilyMiller]

Using a tool or service that generates or modifies text using a large language model

From what I can tell, very nearly every single post about AI rejections that we see here are from people who have either:

• Used Grammarly or Quillbot or some other writing tool to "check their grammar," which turns out to mean they let those tools rewrite sentences and words for them
• Used translation software to translate from their home language into English
• Used Word's copilot writing tools to correct for grammar or other mechanical elements

People don't think of those tools as AI, but they are. Every single one of them now uses an LLM to function. Any time you let a tool modify your text, it's mechanically not any different from letting ChatGPT generate text for you.

And the part about it that sucks is that if you used one of these tools from the very beginning throughout your writing process, there's not really anything you can do to undo it, there's no "original" version that you can revert to.

So of course people get mad and frustrated about that, because the only answer we can give them is "write a new story from scratch and don't use tools."

It’s based on convos held with the site before the current uptick in AI rejections, but I can confirm that what @PennyThompson says is what used to be the main source of rejections in the past.

Then I know at least one writer here whose process I have been privy to that inexplicably got pinged for AI. False positives are inevitable. But I don’t think it’s as easy as deleting a few em dashes.

Whether things have changed, or whether the volume of submissions has gone up,

 

[EmilyMiller]

Oh, and it’s pointless using either free on-line AI checkers or asking ChatGTP whether AI wrote your text. You might as well flip a coin.

 

[EmilyMiller]

Emily: Did AI write my attached text?

ChatMLE: Fuck no! LLMs aren’t that sick in the head! Seek professional help. Do it now!

 

[StillStunned]

Emily: Did AI write my attached text?

ChatMLE: Fuck no! LLMs aren’t that sick in the head! Seek professional help. Do it now!

Can we all just agree not to feed our writing into those things? The Rise of the Machines will be bad enough without them developing weird kinks from our stories.