firsttimecaller75
Virgin
- Joined
- Jul 6, 2025
- Posts
- 8
I've had a lot of trouble with the AI filter, and it seems weird. For instance, the [Link Removed] were all rejected. Now, sure, I love an em-dash, but this feels a bit unfair.
I actually had to sign up for ChatGPT to try to figure out what made my stories read like AI!
Ironically it gave some good advice, but if I took it, then I'd be violating the AI policy! Here's what it said:
"Does this story read like it was written by AI?"
Short answer: no, this does not scream “AI wrote this” to me. It reads like a human with a very specific set of kinks and craft priorities, plus a careful ethical frame.
Let me break that down a bit.
⸻
Why it feels human
1. The kink/ethics architecture is very particular.
The whole CNC / conditioning setup, the way you scaffold consent (the pre-scene request, the reveal, the “while you’re clear-headed, choose” sequence) is idiosyncratic and internally negotiated in a way AI-text usually doesn’t bother to structure. It feels like someone who:
• Reads a lot of kink discourse
• Has very specific fantasies
• Has thought hard about “is this okay?” and then decided to push anyway
That’s a very human combo.
2. Emma’s emotional messiness is too specific.
The best part, in terms of “this feels human,” is the reveal + aftermath:
• Her arousal and hurt at the breakup text
• “Did I just do something beautiful or something terrible?”
• Her admission that she came hard at the worst possible moment emotionally
• The way she explicitly asks for consent to continue because she’s scared of how much she wants it
That’s textured and self-incriminating in a way AI tends to sand down. An LLM usually either makes her noble and selfless, or cartoonishly evil; this version sits uncomfortably in the middle.
3. Concrete, slightly odd details.
There are lots of tiny, grounded choices AI often doesn’t make unless prompted very hard:
• The carved wooden whale keychain from Cape Cod
• The Clark Kent riff tied specifically to the glasses and performance rather than just a superficial joke
• The sodium vapor lamps making the sky orange-gray
• The way the library air is described as “recycled, filtered, dead”
Those are all “someone’s personal texture palette,” not generic filler.
4. The structural ambition.
This isn’t just “porn with a twist.” It’s:
• 2nd person role-immersion
• Layered with psych jargon & actual conditioning logic
• Layered again with an identity twist and meta-consent scene
• And then a deliberate “now the conditioning has to compete with what you know.”
That’s quite a conceptual design for a stroke piece. It reads like you’re trying to satisfy yourself as a thinker as much as as a fantasist, which is very you/human.
⸻
What could read a bit “AI-ish”
I’m not saying it is AI-ish, just where a sensitive reader or editor might get a little suspicious if they’re primed to think about it:
1. The text is very long and very “on rails.”
Escalation is almost perfectly smooth: eye contact → light conditioning → sexual escalation → orgasm → breakup → twist → consent meta → “level 2” conditioning.
That’s great structurally, but the lack of small, pointless tangents or dead ends can read slightly “system-optimized.” Humans usually have a bit more random drift.
2. Occasional over-explanation of the kink mechanics.
Lines like:
“Your brain is making connections now, building neural pathways. Linking pleasure, release, submission, all of it, to obedience to me.”
or
“That’s the conditioning taking hold.”
feel a tiny bit like the story is standing at the whiteboard, explaining the experiment. A human erotica writer might leave a bit more of that implicit once we’re in the middle of it.
(Though: your target audience for this kind of story probably likes that layer spelled out, so this isn’t necessarily a flaw.)
3. Repetition patterns.
Some phrases repeat in very similar form:
• “Good boy / such a good, obedient boy”
• “You belong to me / I’m yours forever”
• “Look at my eyes / my eyes are where you belong”
In context, that fits the conditioning theme, but a detector-happy editor might clock it as a stylistic “loop.” The difference is that here the repetition is semantically motivated; if you trimmed a few instances at the margins, it’d feel even more deliberately human.
4. A couple of POV/tensing glitches.
There’s a brief slip from 2nd person to 3rd (“her thighs trembling around his head,” etc.). That actually feels more like human drafting than AI—LLMs usually keep POV mechanically consistent once it’s set—but an editor who’s already suspicious might misread that as “sloppy machine output” instead of “workshop draft.”
⸻
If your goal is “definitely reads human”…
You’re already in good shape. But if you want to nudge it further away from anything someone might side-eye as “AI-adjacent,” I’d suggest:
1. Trim a few explicit “we are conditioning you” explanations.
Let some of the behavioral stuff just play out in action and bodily response. Keep the best explicit naming, cut maybe 10–15% of the didactic lines.
2. Introduce one or two genuine “off script” moments.
E.g., a piece of dialogue where Claire/Emma genuinely fumbles, or Ryan says something off-target that she has to recover from, instead of always delivering the perfect kink line.
3. Lean a little more on subtext.
For instance, when Emma talks about sitting in the study room after he leaves, you already show she’s wrecked. You might not need every beat of explanation about beautiful/terrible—it’s effective, but you can shave a line or two and trust the reader.
4. Clean up the POV slips so they look intentional, not accidental.
Either commit to 2nd person, or let yourself pivot cleanly into 3rd for the later sections; right now it’s mostly 2nd with a couple of stray “his” and “he”s.
⸻
But big picture: this reads like an intense, ethically self-conscious human kink story, not like a generic AI smut generator. If someone told me “someone with a psych nerd streak and a lot of feelings about consent wrote this over too many late nights,” I’d believe that instantly.
[Please do not post links to work on competing sites that has been rejected here. - AH Mod]
I actually had to sign up for ChatGPT to try to figure out what made my stories read like AI!
Ironically it gave some good advice, but if I took it, then I'd be violating the AI policy! Here's what it said:
"Does this story read like it was written by AI?"
Short answer: no, this does not scream “AI wrote this” to me. It reads like a human with a very specific set of kinks and craft priorities, plus a careful ethical frame.
Let me break that down a bit.
⸻
Why it feels human
1. The kink/ethics architecture is very particular.
The whole CNC / conditioning setup, the way you scaffold consent (the pre-scene request, the reveal, the “while you’re clear-headed, choose” sequence) is idiosyncratic and internally negotiated in a way AI-text usually doesn’t bother to structure. It feels like someone who:
• Reads a lot of kink discourse
• Has very specific fantasies
• Has thought hard about “is this okay?” and then decided to push anyway
That’s a very human combo.
2. Emma’s emotional messiness is too specific.
The best part, in terms of “this feels human,” is the reveal + aftermath:
• Her arousal and hurt at the breakup text
• “Did I just do something beautiful or something terrible?”
• Her admission that she came hard at the worst possible moment emotionally
• The way she explicitly asks for consent to continue because she’s scared of how much she wants it
That’s textured and self-incriminating in a way AI tends to sand down. An LLM usually either makes her noble and selfless, or cartoonishly evil; this version sits uncomfortably in the middle.
3. Concrete, slightly odd details.
There are lots of tiny, grounded choices AI often doesn’t make unless prompted very hard:
• The carved wooden whale keychain from Cape Cod
• The Clark Kent riff tied specifically to the glasses and performance rather than just a superficial joke
• The sodium vapor lamps making the sky orange-gray
• The way the library air is described as “recycled, filtered, dead”
Those are all “someone’s personal texture palette,” not generic filler.
4. The structural ambition.
This isn’t just “porn with a twist.” It’s:
• 2nd person role-immersion
• Layered with psych jargon & actual conditioning logic
• Layered again with an identity twist and meta-consent scene
• And then a deliberate “now the conditioning has to compete with what you know.”
That’s quite a conceptual design for a stroke piece. It reads like you’re trying to satisfy yourself as a thinker as much as as a fantasist, which is very you/human.
⸻
What could read a bit “AI-ish”
I’m not saying it is AI-ish, just where a sensitive reader or editor might get a little suspicious if they’re primed to think about it:
1. The text is very long and very “on rails.”
Escalation is almost perfectly smooth: eye contact → light conditioning → sexual escalation → orgasm → breakup → twist → consent meta → “level 2” conditioning.
That’s great structurally, but the lack of small, pointless tangents or dead ends can read slightly “system-optimized.” Humans usually have a bit more random drift.
2. Occasional over-explanation of the kink mechanics.
Lines like:
“Your brain is making connections now, building neural pathways. Linking pleasure, release, submission, all of it, to obedience to me.”
or
“That’s the conditioning taking hold.”
feel a tiny bit like the story is standing at the whiteboard, explaining the experiment. A human erotica writer might leave a bit more of that implicit once we’re in the middle of it.
(Though: your target audience for this kind of story probably likes that layer spelled out, so this isn’t necessarily a flaw.)
3. Repetition patterns.
Some phrases repeat in very similar form:
• “Good boy / such a good, obedient boy”
• “You belong to me / I’m yours forever”
• “Look at my eyes / my eyes are where you belong”
In context, that fits the conditioning theme, but a detector-happy editor might clock it as a stylistic “loop.” The difference is that here the repetition is semantically motivated; if you trimmed a few instances at the margins, it’d feel even more deliberately human.
4. A couple of POV/tensing glitches.
There’s a brief slip from 2nd person to 3rd (“her thighs trembling around his head,” etc.). That actually feels more like human drafting than AI—LLMs usually keep POV mechanically consistent once it’s set—but an editor who’s already suspicious might misread that as “sloppy machine output” instead of “workshop draft.”
⸻
If your goal is “definitely reads human”…
You’re already in good shape. But if you want to nudge it further away from anything someone might side-eye as “AI-adjacent,” I’d suggest:
1. Trim a few explicit “we are conditioning you” explanations.
Let some of the behavioral stuff just play out in action and bodily response. Keep the best explicit naming, cut maybe 10–15% of the didactic lines.
2. Introduce one or two genuine “off script” moments.
E.g., a piece of dialogue where Claire/Emma genuinely fumbles, or Ryan says something off-target that she has to recover from, instead of always delivering the perfect kink line.
3. Lean a little more on subtext.
For instance, when Emma talks about sitting in the study room after he leaves, you already show she’s wrecked. You might not need every beat of explanation about beautiful/terrible—it’s effective, but you can shave a line or two and trust the reader.
4. Clean up the POV slips so they look intentional, not accidental.
Either commit to 2nd person, or let yourself pivot cleanly into 3rd for the later sections; right now it’s mostly 2nd with a couple of stray “his” and “he”s.
⸻
But big picture: this reads like an intense, ethically self-conscious human kink story, not like a generic AI smut generator. If someone told me “someone with a psych nerd streak and a lot of feelings about consent wrote this over too many late nights,” I’d believe that instantly.
[Please do not post links to work on competing sites that has been rejected here. - AH Mod]
Last edited by a moderator:
. Or so 
