Self-editing using AI

[EmilyMiller]

That sounds painfull for him!

Probably my limitations as a writer (certainly three years ago). No men were harmed in this scene.

 

[Andreas_Kreuz]

From an over-arching, ethical perspective, technology/computers/AI was intended to take the dreary, dangerous jobs away from people.

The ethical perspective is indeed dreary.
I have to use AI at work for Software development. There it is failing miserably. No matter what you do, it cannot be sufficiently precise and correct. So I actually believe we will see that the AI Hype will recede. In real world applications it has failed to live up to its promise. And while the AI companies uphold they can tune their models, they are most likely already at the end of their curve. It has been shown, that more input does not improve the quality anymore.
In this special domain of editing, I believe I could make it to work for me, because the task is simple:
Take an input text, find similar texts in the AI's knowledge base, then look up how these texts have been rated/analyzed (by humans) and transfer (i.e. copy and adapt) the rating to the input text.

 

[EmilyMiller]

the task is simple:

“That is why you fail.”

You acknowledge in a domain you understand that, “it cannot be sufficiently precise and correct.” And yet, in a domain - based on your writing sample - that you have a less firm grip of, you think it’s great.

However, a professional editor (@StillStunned) tells you that AI sucks and you argue with his point of view. Can you see the built in fallacy?

Any expert in a given field laughs at much of what AI produces in that field. It’s only the inexpert who think it is magical.

 

[Andreas_Kreuz]

At some point you will see its limitations the way the rest of us do. But maybe you are some way off from that realization.

If you read my original post it says:

However, there are caveats. AI models are often trained on vast amounts of "flowery" or over-the-top prose, so they might guide you towards a style that's full of clichés or opulent, irrelevant details.

Never follow AI advice blindly. Always ask yourself, "Do I really want this?" ...

 

[Baztrachian]

Anyone who expects AI to improve their creative writing deserves what they get.

AI will due four ewe what Microsoft Spell Check did four ewe.

 

[EmilyMiller]

Is there an AH record for the greatest number of Yoda quotes by one poster on a thread?

 

[Andreas_Kreuz]

However, a professional editor (@StillStunned) tells you that AI sucks and you argue with his point of view. Can you see the built in fallacy?

Well, he (@StillStunned ) tells a professional AI-Prompter what AI cannot do. Can you see the built in fallacy?

 

[EmilyMiller]

If you read my original post it says:

I’m at the ‘whatever’ point of this convo.

 

[AwkwardMD]

I'm having second thoughts about this.

I just watched a short documentary highlighting the development of a line of automation products that establishes new standards for quality leadership and operating excellence. With customer success as their primary focus, work has been proceeding on the crudely conceived idea of a tool that would not only provide inverse reactive current, for use in unilateral phase detractors, but would also be capable of automatically synchronizing cardinal grammeters.

Such a tool, comprised of Dodge gears and bearings, Reliance Electric motors, Allen-Bradley controls, and all monitored by Rockwell Software is Rockwell Automation's Retro Encabulator.

(If you're worried about the side fumbling, just wait. The documentary addresses it)

Basically, the only new principle involved is, instead of power being generated by the relative motion of conductors and fluxes, it's produced by the modial interaction of magneto-reluctance and capacitive duractance. The original machine had a base plate of pre-famulated Amulite, surmounted by a malleable logarithmic casing, in such a way that the two sperving bearings run a direct line with the panametric fam.

The lineup consisted simply of six hydrocoptive marzel veins, so fitted to the ambificient lunar wainshaft that side fumbling was effectively prevented.

The main winding was of a normal Lotus-O deltoid placed in pan-andermic semi-boloid slots of the stater, with every seventh conductor being connected by a non-reversible tremipipe with a differential girdle spring on the up-end of the grammeter. Moreover, whenever fluorescent square motion is required, they may also be employed in conjunction with a drawn-reciprocation dingle arm, to reduce sinosoidal deplanaration.

The Retro Encabulator has now reached a high level of development (and this part is key) and it's being successfully used in the operation of milpher trenions. It'll be available to the public at large very soon, anywhere that the internet is sold.

 

[onehitwanda]

I'm having second thoughts about this.

I just watched a short documentary highlighting the development of a line of automation products that establishes new standards for quality leadership and operating excellence. With customer success as their primary focus, work has been proceeding on the crudely conceived idea of a tool that would not only provide inverse reactive current, for use in unilateral phase detractors, but would also be capable of automatically synchronizing cardinal grammeters.

Such a tool, comprised of Dodge gears and bearings, Reliance Electric motors, Allen-Bradley controls, and all monitored by Rockwell Software is Rockwell Automation's Retro Encabulator.

(If you're worried about the side fumbling, just wait. The documentary addresses it)

Basically, the only new principle involved is, instead of power being generated by the relative motion of conductors and fluxes, it's produced by the modial interaction of magneto-reluctance and capacitive duractance. The original machine had a base plate of pre-famulated Amulite, surmounted by a malleable logarithmic casing, in such a way that the two sperving bearings run a direct line with the panametric fam.

The lineup consisted simply of six hydrocoptive marzel veins, so fitted to the amificient lunar wainshaft that side fumbling was effectively prevented.

The main loading was of a normal Lotus-O deltoid placed in pan-andermic semi-boloid slots of the stater, with every seventh conductor being connected by a non-reversible tremipipe with a differential girdle spring on the up-end of the grammeter. Moreover, whenever fluorescent square motion is required, they may also be employed in conjunction with a drawn-reciprocation dingle arm, to reduce sinosoidal deplanaration.

The Retro Encabulator has now reached a high level of development (and this part is key) and it's being successfully used in the operation of milpher trenions. It'll be available to the public at large very soon, anywhere that the internet is sold.

Is this a cry for help, or for more Absinthe?

 

[Britva415]

If you can prompt an AI, why can't you prompt yourself?

TOTALLY this.

 

[AwkwardMD]

Is this a cry for help, or for more Absinthe?

With side fumbling prevention this good, I may never drink again.

 

[Britva415]

The problem with self-editing, is that in my head I have the consistent image of the scene, but when I write it down, it is something else. And when I read it, I do not recognize what is missing or wrong.

Whatever AI is, it forgodDAMN sure is not a mind reader.

The problem you're describing gets fixed by writing more. Now - it might not be able to fix what you've already written and forgotten what you were thinking when you wrote it, but neither is anyone else - silicon, organic or whatever. No - instead, what I mean is, you just keep practicing until you get better at first-drafting so that the part you wanted to capture gets captured.

 

[AwkwardMD]

Is this a cry for help, or for more Absinthe?

Think how many hamsters this could save.

 

[APilgrimSquare]

I’ve found LLMs can be useful for proofreading and even for some light editorial work: e.g. commenting on the tone of a piece. I have not found it at all useful for creative work beyond things like “suggest a dozen names for working class characters from Pennsylvania born in the 1960s.”

 

[Five_Inch_Heels]

I'm having second thoughts about this.

I just watched a short documentary highlighting the development of a line of automation products that establishes new standards for quality leadership and operating excellence. With customer success as their primary focus, work has been proceeding on the crudely conceived idea of a tool that would not only provide inverse reactive current, for use in unilateral phase detractors, but would also be capable of automatically synchronizing cardinal grammeters.

Such a tool, comprised of Dodge gears and bearings, Reliance Electric motors, Allen-Bradley controls, and all monitored by Rockwell Software is Rockwell Automation's Retro Encabulator.

(If you're worried about the side fumbling, just wait. The documentary addresses it)

Basically, the only new principle involved is, instead of power being generated by the relative motion of conductors and fluxes, it's produced by the modial interaction of magneto-reluctance and capacitive duractance. The original machine had a base plate of pre-famulated Amulite, surmounted by a malleable logarithmic casing, in such a way that the two sperving bearings run a direct line with the panametric fam.

The lineup consisted simply of six hydrocoptive marzel veins, so fitted to the ambificient lunar wainshaft that side fumbling was effectively prevented.

The main winding was of a normal Lotus-O deltoid placed in pan-andermic semi-boloid slots of the stater, with every seventh conductor being connected by a non-reversible tremipipe with a differential girdle spring on the up-end of the grammeter. Moreover, whenever fluorescent square motion is required, they may also be employed in conjunction with a drawn-reciprocation dingle arm, to reduce sinosoidal deplanaration.

The Retro Encabulator has now reached a high level of development (and this part is key) and it's being successfully used in the operation of milpher trenions. It'll be available to the public at large very soon, anywhere that the internet is sold.

Johhny Cash dun bilt his very own AiAi


https://genius.com/Johnny-cash-one-piece-at-a-time-lyrics

 

[AwkwardMD]

Johhny Cash dun bilt his very own AiAi


https://genius.com/Johnny-cash-one-piece-at-a-time-lyrics

I bet that custom one-piece-at-a-time Cadillac would've handled sinosoidal deplanaration like a champ. The rotor arms back in those days were lousy with the kind of quasineutroid noise that negates deplanaration all together, sinosoidal or otherwise.

 

[Andreas_Kreuz]

sinosoidal deplanaration

Ok, now that the trolls took over, we can go to bed.

 

[Five_Inch_Heels]

There's a certain cylindrical redundancy in these threads.

 

[AwkwardMD]

There's a certain cylindrical redundancy in these threads.

Importantly, though, no side fumbling.

 

[Djmac1031]

I've been struggling with writers block for months now. I get ideas, sure, but none of them go anywhere.

Still, I've tried writing them, to the point of frustration when they ultimately grind to a screeching halt.

I just finished writing 4K words worth of story i ultimately decided was crap with no point to it.

4K. Thats FOUR THOUSAND WORDS WASTED because my brain can't find a way forward.

Still, I'd rather publish a shit story, or better yet, not publish anything, than to take story advice/ suggestions from AI.

But hey, that's just me.

 

[alohadave]

Is this a cry for help, or for more Absinthe?

Satire.

https://en.wikipedia.org/wiki/Turbo_encabulator

 

[AwkwardMD]

Satire.

https://en.wikipedia.org/wiki/Turbo_encabulator

The Turbo Encabulator is satire. The Retro Encabulator is the kind of forward-thinking, boot strap initiative we could all take a few notes from.

also ive been drinking

 

[StillStunned]

Well, he (@StillStunned ) tells a professional AI-Prompter what AI cannot do. Can you see the built in fallacy?

I don't recall saying anything about what AI can't do. All I said is that you can do it better yourself.

For instance, you quoted the AI's suggestions for a snippet of text. But when @EmilyMiller suggested improvements, you said that they didn't match what you wanted from the piece:

The cold clinical description is intended. It is the visceral element.

But you also said that Em's improvements were what the AI suggested as well:

And the AI asked the exact same questions as you.

And again, your observations match those of the AI.

So wouldn't it be much better if you, knowing what you intended with a piece of writing, analysed it using the same prompts that you'd otherwise use for the AI?

 

[BobbyBrandt]

I use ProWritingAid (subscription) which is an AI driven ap, when writing. I use it primarily to flag typos (lots) and comma mistakes. (Again, lots). When it flags a sentence as being wonky I look at it myself and try to suss out what the ap didn't like.
I've used it now for over a year, 16+ stories and not one has been kicked back for being AI written.

The flow of a story, the feel of each scene, the mood my descriptions are shooting for ... that's all stuff that I need to learn to self edit in order to get better at what I do. So it's never occured to me to ask an AI to do it for me.

I want a tool I can use to suit my needs, not a crutch I rely on. I have gotten better with my comma use, but I'm not perfect.

I think that you have touched upon a bit of ignored reality: tools that aid us versus generative cheats.

We all employ any number of technological tools to write - from the word processing application with numerous features for formatting and designing the document, to spellcheck, or an app that inserts the desired HTML code for us. I consider these tools of the trade. They rely upon my decisions to implement and achieve the desired function. There are a number of other tools and resources out there, such a ProWritingAid, which provide analysis of the written word without forcing generative content for replacement. There are sites that, for example, analyze the reading level of your writing, (which can be helpful with targeting some of the readers here).

IMO, it boils down to using those tools for analysis only. No generative features at all.