Practical advice for dealing with AI rejection.

[tripleflip]

I agree, as I dont have any of these in mine, and it still gets flagged, I resubmit a few times and it goes through. I wonder if something else is the main cause of this. I.e. the engine gets overwhelmed and starts to spam reject. ? Who knows because nothing comes out of HQ as an explanation.

 

[tripleflip]

How not to look like A I.


I can't say which I find more stupid; using A I. to write a story, or having to comb through a thick fog of bad writing to find evidence of A.I. to use as an objective basis to reject it. Whoever does the latter deserves to be sainted.

Writing is supposed to be a kick. If you let a machine write your story for you, you’re letting a machine get your kicks for you. Unlike human authors, machines don't get kicks. This one fact perfectly explains why they don't write well.

I am a university professor. My field is Low Dimensional Topology, not A I. But my PhD student’s dissertation is on the application of topology to A.I. I am supposed to be her mentor, but she is way smarter than I am. I try to keep up. She works in a 60-dimensional Hamming space. Every word in a story is a vector in this space. Every story is a peculiar arrangement of words, or vectors. in other words, a "solid object" (tensor) which has a distinct “shape,” This 60-dimensional “shape” is not something a human can usefully visualize, but the mathematics of tensors are well understood.

Large Language Models produce story "shapes" recognizably different from the story shapes typical of.human authors. It is easy to show mathematically that human authors using auto-complete, spelling and grammar checking algorithms also tend to produce story shapes different from those typical of human authors not using those aids A statistic my student has developed is the “innovation variance" in a story. Roughly speaking "innovation variance" is the answer to the question: “Given the story so far, how unexpected is the next word the author chooses?”

LLM’s tend more often than not to choose "safe," "low risk,” or "expected” words, from clichés or memes (low innovation); whereas good human writers tend more often than not to choose “high risk” or “unexpected" words. (high innovation)

It seems that to avoid looking like A I. a writer should turn off auto complete, avoid clichés and stale memes and use imaginative word choices. In other words, write well.

Write like a human!

May your words flow easily, as though you were a human getting his, her, it's or their kicks!

Tripleflip

 

[SkyBubble]

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.

The same goes for paragraph length. Sometimes a one-sentence paragraph is all you need. Sometimes it runs over several lines. Try not to make them too long (a lot of people read on a phone) but do vary the length.

 

[SkyBubble]

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

I agree with this. From conversations with LLMs on other topics not related to writing, I've noticed that they LOVE the em dash. It triggers AI detection because all those sites overuse it. I'd also advise leaving space before and after the dash (presumably an en dash if you must use one), as AI usually jams the words together on either side of the dash. (And use those sparingly. If a comma or a colon or some other mark will do the trick, use that.)

AI: that guy---the one she met last week---
A different way: that guy -- the one she met last week --
Or: that guy (the one she met last week)

 

[BeechLeaf]

Grr. If you're actually writing it, and you actually want to use an em dash, use it. Don't let air-raid warnings scare you into changing your style. If you're okay at writing, you're distinctive enough not to be flagged as monotonous.

 

[SkyBubble]

Grr. If you're actually writing it, and you actually want to use an em dash, use it. Don't let air-raid warnings scare you into changing your style. If you're okay at writing, you're distinctive enough not to be flagged as monotonous.

It's just a little safer to use an en dash.

 

[SkyBubble]

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.

I find that advice solid, helpful, and comprehensive.

 

[SkyBubble]

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

Then what do you think is responsible?

 

[Alara_KL]

Just a short idea that worked for me:
I got very frustrated when my first story here (completely AI-tool free, but non-English, where this seems to be an even bigger issue) kept getting rejected again and again for weeks, even with rewrites.
I then just continued the multi-part story and bundled the first two parts into one of double the size. This then went through without issue (as did the subsequent parts).

 

[sirhugs]

Building replicas of radio transmitters out of coconuts and bamboo is doing something too, but it's not strongly correlated with how many airplanes fly overhead

been watching Gilligan's Island reruns again?
Always a good source of inspiration...

 

[Lucian_Devine]

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.

There are other ways to handle the "he said" "she said" without entirely skipping it and going straight to the action of shaking the head like you had Derick do as well. One thing that I like to do, is go with something like, "God I love you..." Lucian started, giving Luciana a firm and passionate kiss, "...more and more every day...", he continued after tearing his lips from hers and buried himself in her neck.

Started, continued, and finished are a great way to break the monotony of "he said" "she said", especially when used together, as well as just using other words. He can murmur, softly stammer, st-stutter, shout, scream, whisper heatedly against her neck, etc. Then there's also the simple thing of trying not to start too many paragraphs in a row with the same word. I try to at least go every other. So, if I start a paragraph with "Lucian doing X", I try to start the next paragraph with, "While Lucian was doing X." It seems so minor, but it makes such a big difference.

People also get so invested with what a character is doing physically, that they forget about the little things, a character's eyes. Simply having a character's eyes flick up to meet your partner's, flit away nervously, dropping down out of deference. The more words you can use, preferably without having to use any sort of spellchecker, the better, because if it comes from your brain, it's less likely to trigger an AI check. You don't always have to involved every part of your character, but when the scene demands it, or when you are trying to stretch out a post from a single paragraph, getting their eyes involved, their inner thoughts and reflections, etc, more is better.

~LD