Using AI as a reviewer to improve my writing

Sure! "People's approach to AI often mirrors their view of life: bitter nihilists see it as a mistake rather than a gift."

That's the hallmark of AI-generated snarky content...
Hah! So you are dissing AI now? You can't have it both ways.
Well, you can actually if that's your thing ;)
 
I don’t see any disadvantages to AI, just as I don’t see any to the keyboard. Anyone who prefers to stick with their quill is more than welcome to do so.
Learning, for example. While AI in the hands of highly educated experts might lead to some new insights in certain branches of science, the masses, to quote Noam Chomsky, will use it to avoid learning. It's a legitimate point of concern.
 
Ugh! We're done.
Awww... you people and your left and right bollocks. The man is a giant of an intellectual, and if we must go there, he has always represented the progressive but healthy left. There is good on both sides. But yeah, better not to push this topic here.
 
I mean, pick one: We can take it seriously when AI says AI can’t understand emotional depth (which it has seen stated before in text it was trained on), or, we can take it seriously when it says “this particular piece of writing lacks emotional depth” - which it has seen before in reviews it was trained on, but has never seen before in regard to the new piece in question.

It’s definitely a matter of “this is something a revewer would say, generically” and not “this is something a reviewer would think about this.”


It’s interesting, though, how AI ‘reviews’ reviews to decide what is the most appropriate response. It’s almost like crowd sourcing in a way while also being the antithesis.

Don’t discount the fact that AI is still rapidly developing, version 4 is far superior to version 3 while version 5 will be released soon. It’s supposed to have the ability to keep track of much longer conversations and information shared throughout various threads - leading presumably to better tracking of context and facts, creating lees need for hallucinations to fill gaps. It’s being marketed in many ways including as a better customer service representative replacement that can work 24/7 and be instantly trained and track new information in real time while being able to reflect on the customer’s expressed needs and desires while tracking cues and adjusting responses to their emotional state.

This shit will get much better in a short amount of time, including being able to better interpret and react to human emotion, simply because that is something being requested of it.

Prompts with requests to provide only factual responses or based on peer reviewed information are easy to craft. You can request that it write stories about particular characters in particular situations based on a variety of styles that will produce results which will only continue to improve. The fact that some AI generated works already slip through detection is a mere harbinger of what is to come.
 
I just tried feeding my latest work in progress to ChatGPT for a review.

The response was much more encouraging than I usually get for my Loving Wives stories!!! (Of course, it doesn't take much to be better than a comment like "Eat Shit and Die!")
 
I just tried feeding my latest work in progress to ChatGPT for a review.

The response was much more encouraging than I usually get for my Loving Wives stories!!! (Of course, it doesn't take much to be better than a comment like "Eat Shit and Die!")

Try entering a descriptive passage with a lot of scenery and ask it to provide an image based on a particular character’s perspective. 😉
 
ME:
Produce an image based on the following excerpt from a fictional story:
———

The carnival rides come into view and we turn off the Pacific Coast Highway. As we drive through town we can see the Ferris wheel, a roller-coaster and several other rides on the midway of the pier. There is a good sized amphitheater, and two rows of stores and restaurants running out several hundred yards over a wide yellow-sand beach, into the Pacific Ocean.

ChatGPT4 (free version)

IMG_7043.jpeg

Not exactly as I pictured but not bad, and far better than I can draw. It definitely gives me some feedback to how well my description comes across.
 
ME:
Produce an image based on the following excerpt from a fictional story:
———

The carnival rides come into view and we turn off the Pacific Coast Highway. As we drive through town we can see the Ferris wheel, a roller-coaster and several other rides on the midway of the pier. There is a good sized amphitheater, and two rows of stores and restaurants running out several hundred yards over a wide yellow-sand beach, into the Pacific Ocean.

ChatGPT4 (free version)

View attachment 2449608

Not exactly as I pictured but not bad, and far better than I can draw. It definitely gives me some feedback to how well my description comes across.
Pay graphic artists.
 
Version 5 is suppose to be good at producing videos too. 🤷‍♀️

(And don’t use automated checkout at the grocery store.)
I make it a point to go to an actual person. Someone working because they have a family to support.

Whatever it is you do for a living, enjoy being unemployed when your precious advances take your job away because AI Alex doesn't require a paycheck, need time off or whine.
 
I make it a point to go to an actual person. Someone working because they have a family to support.

Whatever it is you do for a living, enjoy being unemployed when your precious advances take your job away because AI Alex doesn't require a paycheck, need time off or whine.

Right?

The thing about freedom and a market based economy is that anytime a new technology can save money by increased productivity, more convenience, and lower labor costs, business will have incentive to pay fewer people for their services.

You can make all of your altruistic choices for supporting your neighbors but the bottom line is…. the bottom line. 💰

(Unless you support protective regulations) 😉
 
Of course AI cannot judge emotional depth, just like it cant hot or cold.
"Lacking emotional depth* or any other judgement has to be read this way:
The reviewed text has a similarity with other texts, that human reviewers considered to lack emotional depth.
And that is enough to take look at how my story conveys emotions.
 
Of course AI cannot judge emotional depth, just like it cant hot or cold.
"Lacking emotional depth* or any other judgement has to be read this way:
The reviewed text has a similarity with other texts, that human reviewers considered to lack emotional depth.
And that is enough to take look at how my story conveys emotions.

True enough, but there are endless ways to craft a prompt.

“What elements of this excerpt are bored housewives most likely to connect with? What parts might detract from their interest in continuing?”
 
Random research for a story detail?

Me:
What kind of fish are you most likely to catch using a rod and hook while using a marshmallow for bait in Boston Harbor?


ChatGPT:
Using marshmallows as bait in Boston Harbor isn’t typical, but it can still attract certain fish, especially ones with a curious or opportunistic nature. You’re most likely to catch species like:


1. Sunfish - Though they’re more common in freshwater, sunfish in brackish areas might be curious enough to bite.


2. White Perch - Found in brackish and coastal waters, they’re opportunistic feeders and might be attracted to unusual bait.


3. Striped Bass (schoolies) - While marshmallows aren’t their first choice, smaller, younger striped bass might take a nibble if they’re especially curious or hungry.


If you’re set on catching fish in Boston Harbor, consider switching to more common bait like squid, seaworms, or cut bait, which are more likely to appeal to local saltwater species like flounder, scup, or mackerel.



(Fact check anything you need to be sure of.)
 
I am forced to deal with AI, because I work in IT, where AI code generation might have an impact on the work environment. Of course my management asks me if AI can make us more profitable. And yes it can. It can make a good programmer faster, but it can not replace him/her. In IT we are lucky insofar, as there is a hard criterium to evaluate AI quality: Either the generated code solves the problem or it doesnt. Emotional depth is a lot harder to evaluate.
 
So Literotica tries to keep out AI stories, which I am very happy about. Whether the AI rejection process is effective is not the topic of this post.
Instead of using AI to write stories, I have tried to use AI to review my stories so I can learn and improve. Researchers have suggested that AI is an excellent trainer because it allows you to create so-called "optimal challenge points".

Have they provided evidence to support that?

So I write a first version and then post it to GPT asking it for feedback on the writing style.

Asking GPT for feedback on your writing is kind of like asking Hugh Laurie for a medical diagnosis. He's worked hard on learning how to look like a doctor, he knows the words doctors use and can say Doctor Things like "10 ccs morphine, stat!" But his mission is not to give you accurate medical advice, it's to do a convincing impression of a doctor. Taking that advice might be bad for your health.
 
True enough, but there are endless ways to craft a prompt.

“What elements of this excerpt are bored housewives most likely to connect with? What parts might detract from their interest in continuing?”
I love that prompt. I modified it somewhat and applied it to my orginal test story.
What elements of this story are underfucked shy nerds most likely to connect with?

Awkward Sexual Exploration: The characters’ hesitancy and struggle to communicate fantasies mirror shy nerds’ own experiences.
Structured Dynamics: The clear rules of BDSM appeal to readers who find comfort in defined roles and boundaries.
Imaginative Role-Play: The prostitute scenario offers a safe, thrilling escape for readers hesitant to explore such fantasies in real life.
Validation and Approval: The male protagonist’s pride in the female character resonates with readers seeking affirmation in relationships.
Relatable Outsiders: The characters’ long-distance relationship and use of a second language may connect with socially isolated readers.
Public Scenarios: Exhibitionist scenes provide a vicarious thrill for those fantasizing about attention but too inhibited to seek it.

Pretty much spot on.
 
I'm not going to give you any grief, but I'd prefer that you not do that.
No worries. That was something, that did not work. And your texts will have been read by the ai engines anyway, because you published them on the literotica site, not because I put a few paragraphs of yours in a prompt.
 
Me:
Can you review stories on the Literotica website?


ChatGPT:
I can provide feedback or analysis if you share the text or give me a summary of the story you’re referring to, but I can’t directly browse or access content from Literotica or other similar websites. Let me know how you’d like to proceed!
 
Me:
Can you review stories on the Literotica website?


ChatGPT:
I can provide feedback or analysis if you share the text or give me a summary of the story you’re referring to, but I can’t directly browse or access content from Literotica or other similar websites. Let me know how you’d like to proceed!
just because it says it can't access the site doesn't mean it isn't accessing the site. This is likely one of the ring fences put up by the developers to try to prevent model poisoning. There will be massive ETL processes running in the background to feed the basilisk.
 
Way back when, Google Translate used to have a provision in its Terms of Use that said, effectively, everything you uploaded became their property. I had to point out to clients several times that all those confidential client memos they were running through Translate weren't quite as confidential as they hoped.

Same for DeepL. It says the professional version won't use your texts, but I've seen evidence to the contrary.
 
Back
Top