Print Topic

SimplyScripts Screenwriting Discussion Board  /   General Chat  /  Greenlight Coverage (AI)
Posted by: ajr, January 21st, 2024, 5:29pm
Hi, all -

Anyone have experience with this?

Tells you it's "free", and spits out coverage within minutes (which it does)/

So the "free" is "what works". And it's pretty accurate. Honestly, I was shocked.

Everything else - synopsis, how to improve, budget, casting suggestions, and score per category, etc. are $45 per script.

It's not a lot of money... but I'd rather put that toward film festivals for my short film... unless a good score on this site is the shyte for producers and financiers.

Any other experiences?

Thanks,

AJR
Posted by: LC, January 21st, 2024, 5:53pm; Reply: 1
Are you tired of waiting for readers (humans) to get back to you...?
So this is like a drive-through fast food assessment of your work. Satisfying, but basically junk that your Mum would have told you.

It tells you what works but not what doesn't? That you pay for. And that would be the litmus test.
For now it gives you what you want to hear, free compliments and praise so you're suckered into paying.

Really? We should boycott this BS.
Never heard of it until you posted AJR. And I can't work out if you're for it or against it.
Posted by: ajr, January 21st, 2024, 6:02pm; Reply: 2
Hi, LC!

I'm very much against it... until today LOL.

Here's the thing - a reader is one person's opinion. I don't put much stock in that.

What I DO put stock in is what the industry puts stock in. And Greenlight has a quote from Scott Mednick, producer of among other things TMNT who sings its praises. So, if this is the industry shortcut? Then we all have to conform.

AJR
Posted by: AnthonyCawood, January 21st, 2024, 6:29pm; Reply: 3
I think you are going to see more and more of this sort of thing, and some of it may prove useful in terms of helping identify general issues with a script.

But as Libby said, this is generic, fast-food type feedback, depth and specifics are lacking.

Greenlight Coverage uses OpenAI under the hood (says so on their Terms page), so they are just using ChatGPT for the coverage element/feedback.,

Here is feedback from the 'Creative Writing Coach' a specifically trained GPT created by Open AI, on one of my recent scripts on here (Freshbloom), and you can see the prompt I used...

Please give me an industry-standard assessment of this script, please focus on the areas to improve in it and be as specific as possible.

Based on the script "Freshbloom" by Anthony Cawood, here is an industry-standard assessment with a focus on areas for improvement:

Strengths of the Script:

Concept: The script presents an intriguing and unique concept. The presence of 'TODAY' badges and the interaction between characters around this concept are engaging and thought-provoking.

Character Development: The characters, particularly Travis and Kira, are well-established with distinct personalities and emotional depth.

Dialogue: The dialogue is natural and flows well, contributing to character development and advancing the plot.

Areas for Improvement:
Scene Descriptions: While the descriptions set the scene, they could be more vivid and detailed to enhance visual imagery. For example, more descriptive language could be used to paint a clearer picture of the urban park and the emotions it evokes.

Pacing and Structure: The script would benefit from a more defined structure, particularly in its pacing. Some scenes may require tightening to maintain momentum and keep the audience engaged.

Character Backstories: While the characters are interesting, their backstories and motivations could be further developed. This would add depth to their interactions and decisions, especially regarding the significance of the 'TODAY' badges.

Conflict and Stakes: The script could amplify the central conflict and raise the stakes to create more tension and investment in the outcome. It's crucial for the audience to understand the implications and consequences associated with the badges.

Climactic Moments and Resolution: The script could benefit from a more impactful climax and resolution. Ensuring that these moments are emotionally resonant and provide closure to the story�s thematic elements would strengthen the overall narrative.

Additional Suggestions:
Consider adding more subtext in the dialogue to reveal characters� internal struggles and histories indirectly.
Introduce additional plot elements or twists that align with the central theme to keep the narrative dynamic and unpredictable.
Explore the broader world or society in which this story takes place to give context to the significance of the 'TODAY' badges.

Overall, "Freshbloom" has a compelling premise and strong character interactions. With refinements in scene descriptions, pacing, character depth, and the development of conflict and resolution, it has the potential to be a highly engaging and thought-provoking piece.


The feedback is very surfacy, and despite me asking for specifics I don't really get any... better feedback from SS imho
Posted by: LC, January 21st, 2024, 7:46pm; Reply: 4
Ant, that critique, like you say is very generic.
You could have a better climax, you could consider more subtext, you'd probably benefit from amplifying this or that. There are no specifics, and no examples. It just basically says: Good job, buddy! But always room for improvement.

AJR, do you actually know Scott Mednick endorses this? Anyone can type in someone's credentials.

Perhaps this is the way of the future if badly written scripts need to pass AI evaluations before they will get properly read by Production Companies and they're going to have their go-to place of which you must pass muster first.

I'd be interested to see an evaluation of a badly written script - with mistakes galore.

I got into an 'argument' with ChatGPT the other day. I thought from a purely analytical level it could answer a word usage/grammar question. I knew instinctively what the correct usage was so I didn't go with it's automatic response.

I think I posted this before but I find it amusing so will post again:

User
Him and Paul are going to be fighting over those top leading man roles for the next couple of decades.

Is this grammatically correct?

ChatGPT
Yes, your sentence is grammatically correct. However, for clarity, you might consider adding a comma after "Him" to make it "Him, and Paul are going to be fighting over those top leading man roles for the next couple of decades."


User
Is it not He and Paul are going...?

ChatGPT
You're correct. The grammatically correct form is "He and Paul are going to be fighting over those top leading man roles for the next couple of decades." Thank you for pointing that out.

User
Well which is it, he or him?

ChatGPT
I apologize for any confusion. The correct usage is "He and Paul are going to be fighting over those top leading man roles for the next couple of decades." "He" is the subject pronoun used when the person is the subject of the sentence.


User
Glad you learned something.

ChatGPT
As a machine learning model, I don't learn in the traditional sense, but I'm here to provide information and assistance. If you have any more questions or if there's anything else I can help you with, feel free to let me know!

Is this conversation helpful so far?

Message ChatGPT…

ChatGPT can make mistakes. Consider checking important information.

Yes, I will.  ;D
Posted by: Grandma Bear, January 21st, 2024, 8:11pm; Reply: 5
I asked ChatGPT to read one of my shorts once, and it basically told me I was great. I immediately became suspicious and distrusted it. Now, I'm in a different position. Two of my go-to people for input are busy doing completely different things, so I have no one to ask for feedback. I might give this a try again because otherwise, I'm just operating in a vacuum, totally clueless.  
Posted by: LC, January 21st, 2024, 8:35pm; Reply: 6

Quoted from Grandma Bear
I asked ChatGPT to read one of my shorts once, and it basically told me I was great. I immediately became suspicious and distrusted it. Now, I'm in a different position. Two of my go-to people for input are busy doing completely different things, so I have no one to ask for feedback. I might give this a try again because otherwise, I'm just operating in a vacuum, totally clueless.  

I gather you don't want to put the script up for feedback on SS and are keeping it on the down low?

Posted by: kcranford, January 21st, 2024, 8:35pm; Reply: 7
[quote=

I'd be interested to see an evaluation of a badly written script - with mistakes galore.


[/quote]

Maybe I could submit something. I have a few that would meet this qualifier.  :-/
Posted by: LC, January 21st, 2024, 8:57pm; Reply: 8
You don't qualify, Kathy.
You're too good a good writer and have the mug to prove it.  :D

I think we'd have to concoct something with all the typical Newb mistakes and a really bad plot to boot; see how glowing a review it gives that.
Posted by: kcranford, January 21st, 2024, 9:02pm; Reply: 9

Quoted from LC
You don't qualify, Kathy.
You're too good a good writer and have the mug to prove it.  :D

I think we'd have to concoct something with all the typical Newb mistakes and a really bad plot to boot; see how glowing a review it gives that.


What a scathingly awesome idea!  Let’s do it!
Posted by: Grandma Bear, January 21st, 2024, 9:58pm; Reply: 10

Quoted from LC

I gather you don't want to put the script up for feedback on SS and are keeping it on the down low?

I think I did put it here sometime last spring or summer. It was when I posted a bunch of shorts in a short amount of time. Don't remember which script it was though.
Posted by: AlsoBen, January 21st, 2024, 10:52pm; Reply: 11
I posted a thread or two about the AI script reading services.

Initially I was impressed, but that was more about the fact that the program can actually follow along with a story and summarise it accurately, and — not unlike grammarly — is good with grammar issues. It also seems able to identify pacing issues and plot threads that are resolved or unresolved. Which is genuinely impressive for AI.

The fundamental issue IMO is that it cannot really identify whether a writer is good. By which I mean, any amateur can write a script that is technically correct and follows a 3 act structure (especially if they’re a stickler like with the Save The Cat formula). Bad writers are formulaic and AI seems to actually like formula.

It has no sense of a writer’s voice because it would need to be able understand dynamically how the word usage, language, creative choices etc all tie together into something more nebulous that AI doesn’t yet grasp. At least a paid human reader can tell you “hey this script might not be perfect but there’s something about your voice that is compelling”.
Posted by: LC, January 21st, 2024, 11:12pm; Reply: 12

Quoted from ajr
Hi, all -

Anyone have experience with this?

Tells you it's "free", and spits out coverage within minutes (which it does)/

So the "free" is "what works". And it's pretty accurate. Honestly, I was shocked.

Everything else - synopsis, how to improve, budget, casting suggestions, and score per category, etc. are $45 per script.

It's not a lot of money... but I'd rather put that toward film festivals for my short film... unless a good score on this site is the shyte for producers and financiers.

Any other experiences?

Thanks,

AJR

I was quite busy automatically criticising this.
I'm curious AJR what shocked you by way of accuracy or anything else?  And what impressed you?

Posted by: kcranford, January 22nd, 2024, 9:19pm; Reply: 13
I swear you are all leading me down the road of perdition with all this AI stuff.  But not being one with any fortitude to resist temptation, I tried the "free" version of a script review.  Of course, it only gives you a glimpse and then teases you with revealing the rest of its "thoughts" for a fee, but nonetheless, here is what it said about my script, "With Love, From Romance"

Plot Assessment and Enhancement
What is working well:

- The concept of the story revolving around the town named "Romance" and its associated legend about a lost wedding ring is intriguing. This provides a nice romantic backdrop.

- The meet-cute between the main characters Avery and Bryce via her getting a speeding ticket is cute and entertaining. Their banter and slowly developing connection is enjoyable.

- The mystery surrounding the lost ring and Avery uncovering clues about it keeps the reader engaged. The reveal of the ring's location in the dog's locket is a nice surprise.

- The incorporation of historical elements like the World War I soldier Patrick and his fiancée Emma into the town's backstory gives depth. The connection to Bryce's Aunt Sue is also nice.

- The ending with Avery and Bryce getting married on Valentine's Day, along with the gift of a new puppy named Chroi, ties the story together nicely.

Pretty uncanny. Of course I'm tempted to pony up the extra dollars to see what the machine "thinks" about my work. In addition to being extra creepy, this AI thing is actually addicting, and that in itself is creepy.  Anyway, I'll think about whether I want to pay the $45.00 to hear its "opinion".  What I'm also thinking is that this whole thing could make a great short about gullible writers getting sucked into the compelling vortex of AI gratification.  Possibly coming soon to an OWC near you.  :o
Posted by: AnthonyCawood, January 23rd, 2024, 3:25am; Reply: 14
Yep, AI is definitely addictive ;-)
Posted by: zi94sm65, January 26th, 2024, 12:51pm; Reply: 15
Like Kathy, i was curious, so i tried the free Greenlight Coverage and put in a script i wrote. It literally mirrored the words from my script in its "assessment": my narrotor character has a line, "Cultural clashes and the tensions of class paint a portrait of a town struggling to reconcile the old with the new."
It spits this out:
Plot Assessment and Enhancement
What's working well:
- The setting of 1890s small-town Wooster, Ohio provides an interesting historical backdrop of cultural clashes and tensions between old and new.
- The newsboy Nate character introduces some of these tensions and acts as a device to set events in motion.
- The conflict sparked by Italian Mike's attempted break-in and attack on George Massoni makes for a dramatic sequence. The escalating fight scene is intense.
- The various eyewitness accounts from different perspectives build mystery and intrigue around what exactly happened.
- The political motivations of the Mayor and police add an additional layer of complexity to the case.

It got so much wrong in this assessment and it's understanding of the script that i wouldn't pay to see what else it has to say. Of course my script could have just been really bad and it was just giving me back what i gave it: garbage.
Posted by: LC, January 27th, 2024, 4:19am; Reply: 16
Yep, I think at this point it basically regurgitates what's in your script in a complimentary way. Sometimes says you could add more.

Flatters you so you go back for more.  ::)
Posted by: JackFromGreenlight, February 4th, 2024, 10:30am; Reply: 17
Hey guys, thanks so much for the comments.  I am the founder of Greenlight Coverage and would love to clarify that - We do use some OpenAI functions, but our core model is actually proprietary, you will find OpenAI is much more generic than our output.   Happy to answer any other questions you guys have =)
Posted by: ghost and_ghostie gal, February 4th, 2024, 5:26pm; Reply: 18

Quoted from JackFromGreenlight
Hey guys, thanks so much for the comments.  I am the founder of Greenlight Coverage and would love to clarify that - We do use some OpenAI functions, but our core model is actually proprietary, you will find OpenAI is much more generic than our output.   Happy to answer any other questions you guys have =)


Ahoy JackFromGreenlight - thanks for the clarification. :)-Andrea

Posted by: LC, February 4th, 2024, 6:35pm; Reply: 19

Quoted from JackFromGreenlight
Hey guys, thanks so much for the comments.  I am the founder of Greenlight Coverage and would love to clarify that - We do use some OpenAI functions, but our core model is actually proprietary, you will find OpenAI is much more generic than our output.   Happy to answer any other questions you guys have =)

So, how is it trained (for want of a better word) to be better and less generic?
Posted by: JackFromGreenlight, February 4th, 2024, 6:49pm; Reply: 20

Quoted from LC

So, how is it trained (for want of a better word) to be better and less generic?


Yea, so we worked with many industry veterans when we trained and programed our system.  It is largely driven by their feedback and adapted to what a industry professional would want to see in a coverage report.
Posted by: JackFromGreenlight, February 4th, 2024, 6:50pm; Reply: 21



Ahoy JackFromGreenlight - thanks for the clarification. :)-Andrea



You are welcome =)
Posted by: ajr, February 4th, 2024, 7:06pm; Reply: 22

Quoted from LC

I was quite busy automatically criticising this.
I'm curious AJR what shocked you by way of accuracy or anything else?  And what impressed you?


Hi, Libby - as Kathy said, the "what's working" was pretty uncanny. Or was it easily discovered? Hard to tell. It does seem like it repeats the same adjectives. For example, I noticed 'intriguing' on this thread, and also in mine.

The characters are colorful, quirky, and compelling. Their dynamics and relationships are complex and intriguing.

- The dialogue is sharp, humorous, and reveals the distinct personalities.

- The time period details of the late 80s/early 90s are fun and nostalgic.

- The scavenger hunt plot device is a clever way to propel the characters into funny and surprising situations.

- The story explores meaningful themes about friendship, loss, life choices, and personal growth.

- The ending montage provides satisfying resolution for the main characters.


Question for Jack from Greenlight - I'm not so much interested in Greenlight's opinion on how to improve the script, as I've had attachments before and received a ton of notes and have rewritten it for certain people, etc. - as I am about how much industry cache a good score has.

You have a quote from Scott Mednick who is a pretty big-time producer. Does that mean if I get a good score, it's a marketing tool with which to approach someone like Scott?

Thanks,

AJR
Posted by: Gum, February 4th, 2024, 7:30pm; Reply: 23
Hi all. Since AI seems to be the flavor of the week, thought I’d post my own findings to maybe quell or stoke anyone’s interest should they be thinking of using an AI service for script feedback.

I recently used the Greenlight AI Feedback service, and to date… it is the only feedback service I’ve ever paid for regarding a screenplay. Human or AI. Considering the script is about 7 years old and I’ve never had feedback on the script in its entirety, I thought what the heck, let’s see what AI does with 130pgs of surreal dreamscape.

Anyway, the end result for what I paid is more than satisfactory for what I was looking for. Alot of groovy feedback for the price, and it (most importantly) showed me where the script is and is not working, err… optimally.

As well, it allowed 3 additional questions after feedback regarding areas of the script, areas that I was really curious to have detailed with another’s opinion to see if it would give me additional ideas for those scenes, or information that would allow me to build on or reconstruct similar scenes elsewhere in the script.

It even spit out a succinct logline that pretty much resonates with the script.

Original logline (that it never prompted for):

“Inspired by the surreal works of Lewis Carroll and L. Frank Baum: A small town girl who dreams of traveling to distant lands, suddenly finds herself on an epic quest to release her lost love from the prison of an underworld garden matrix.”

Greenlight AI Logline:

“After a young woman enters a magical realm to find her lost love, she must defeat the evil overlord who has imprisoned him and restore balance to the mystical gardens.”

So, yeah, anyway that feedback is here if anyone is curious what Greenlight AI Feedback looks like, as well as the original script if anyone’s curious as to what the AI is actually giving feedback on…

Feedback: https://www.dropbox.com/scl/fi/q11l9f7axhsx0kwu9zc29/Greenlight-AI-Feedback-The-Arpeggio-Garden.pdf?rlkey=74di5khuo9bxigdl5ja26vwcj&dl=0

Script ‘The Arpeggio Garden’: https://www.dropbox.com/scl/fi/inj7f4onvs7fhawjhwavc/The-Arpeggio-Garden.pdf?rlkey=mgajw2hcoocoh3909wt35e0o2&dl=0

Hopefully this helps, best of luck…
Posted by: LC, February 4th, 2024, 7:31pm; Reply: 24

Quoted from ajr


Hi, Libby - as Kathy said, the "what's working" was pretty uncanny. Or was it easily discovered? Hard to tell. It does seem like it repeats the same adjectives. For example, I noticed 'intriguing' on this thread, and also in mine.

The characters are colorful, quirky, and compelling. Their dynamics and relationships are complex and intriguing.

- The dialogue is sharp, humorous, and reveals the distinct personalities.

- The time period details of the late 80s/early 90s are fun and nostalgic.

- The scavenger hunt plot device is a clever way to propel the characters into funny and surprising situations.

- The story explores meaningful themes about friendship, loss, life choices, and personal growth.

- The ending montage provides satisfying resolution for the main characters.





Thanks, AJR!
All of that just seems really generic to me.


Quoted from ajr

Question for Jack from Greenlight - I'm not so much interested in Greenlight's opinion on how to improve the script, as I've had attachments before and received a ton of notes and have rewritten it for certain people, etc. - as I am about how much industry cache a good score has.

You have a quote from Scott Mednick who is a pretty big-time producer. Does that mean if I get a good score, it's a marketing tool with which to approach someone like Scott?

Thanks,


I'm interested in the answer to this question too.

I'm curious to know if this is going to become the way of the future e.g. getting a minimum score from AI before you can progress with certain things.

I still think the test of this would be to have AI access a really badly written script.

Posted by: ajr, February 4th, 2024, 7:34pm; Reply: 25
It looks like AI is programmed to spit back 5-7 answers about what's working, regardless.

I suppose the less effusive the comments, and the less complimentary the adjectives, the more AI thinks it's a bad script...?

AJR
Posted by: LC, February 4th, 2024, 7:41pm; Reply: 26

Quoted from ajr
It looks like AI is programmed to spit back 5-7 answers about what's working, regardless.

I suppose the less effusive the comments, and the less complimentary the adjectives, the more AI thinks it's a bad script...? AJR

You mean if you can't say anything nice don't say anything at all?  ;D

Just looked at Rick's (Gum) Coverage and that is way more impressive and detailed. Out of curiosity what did that cost, Rick?

Posted by: Gum, February 4th, 2024, 8:28pm; Reply: 27

Quoted from LC

Just looked at Rick's (Gum) Coverage and that is way more impressive and detailed. Out of curiosity what did that cost, Rick?


Hey, Libby,

Yes, I agree… it’s quite detailed, and came with some bonus info that I didn’t even consider, like casting (personality types, etc) that could actually help someone flesh out a script if you were to base your scripts protagonist or antagonist on a certain actor’s screen personae. Then there’s the Comparative Film Analysis which could help to further drill down the plot or thesis-antithesis-synthesis of your own 3 act screenplay in some shape or form I would imagine.

I paid $45 (probably $45 USD online which equates to about $60 CAD on my end) for 1-time feedback on 1 script, and it was ready in about 2 hours for the full feedback, then allowed 3 additional questions that it answered in real time as I asked them.

I honestly don’t think I would have gotten that type of detailed feedback for less than a few hundred bucks from an online service where an actual person read it, and I certainly wouldn’t get that via quid pro quo… so, yeah, it was definitely worth it in this particular instance.

Hope this helps  :)
Posted by: LC, February 5th, 2024, 12:15am; Reply: 28
Very reasonable price. Just remember it ain't human.

I did love all the suggested casting it did. :)
That was cool.
Posted by: Gum, February 5th, 2024, 5:51pm; Reply: 29

Quoted from LC
Very reasonable price. Just remember it ain't human.


True, and for what the feedback is worth I would only use it for features, not short scripts. I do have a couple other features that I might throw at it, just to see how the feedback would compare from one to the other.

Heck, even if I shell out another $120 CAD for feedback on a couple more scripts, that’s still less than I usually spend on a week’s supply of sugar, grease, nicotine, alcohol, and caffeine: my five basic food groups, lol.

Thanks for the input! :)
Posted by: JackFromGreenlight, February 5th, 2024, 9:07pm; Reply: 30

Quoted from ajr


Hi, Libby - as Kathy said, the "what's working" was pretty uncanny. Or was it easily discovered? Hard to tell. It does seem like it repeats the same adjectives. For example, I noticed 'intriguing' on this thread, and also in mine.

The characters are colorful, quirky, and compelling. Their dynamics and relationships are complex and intriguing.

- The dialogue is sharp, humorous, and reveals the distinct personalities.

- The time period details of the late 80s/early 90s are fun and nostalgic.

- The scavenger hunt plot device is a clever way to propel the characters into funny and surprising situations.

- The story explores meaningful themes about friendship, loss, life choices, and personal growth.

- The ending montage provides satisfying resolution for the main characters.


Question for Jack from Greenlight - I'm not so much interested in Greenlight's opinion on how to improve the script, as I've had attachments before and received a ton of notes and have rewritten it for certain people, etc. - as I am about how much industry cache a good score has.

You have a quote from Scott Mednick who is a pretty big-time producer. Does that mean if I get a good score, it's a marketing tool with which to approach someone like Scott?

Thanks,

AJR



Great question AJR!

I heard a lot of similar demands from users actually, and we are already working on a screenplay contest that will make this happen.  So we have assembled a Greenlight Committee consists of a group of highly regarded industry veterans and some of them are even currently head of content/film finance/gate keepers of production/financing companies.  Finalists of this contest will be given opportunity to get feedback from the committee as well as ask additional questions, so they can help you push your project forward by giving you feedback/credibility etc.  Please stay tuned =)

Posted by: JackFromGreenlight, February 5th, 2024, 9:10pm; Reply: 31

Quoted from Gum
Hi all. Since AI seems to be the flavor of the week, thought I’d post my own findings to maybe quell or stoke anyone’s interest should they be thinking of using an AI service for script feedback.

I recently used the Greenlight AI Feedback service, and to date… it is the only feedback service I’ve ever paid for regarding a screenplay. Human or AI. Considering the script is about 7 years old and I’ve never had feedback on the script in its entirety, I thought what the heck, let’s see what AI does with 130pgs of surreal dreamscape.

Anyway, the end result for what I paid is more than satisfactory for what I was looking for. Alot of groovy feedback for the price, and it (most importantly) showed me where the script is and is not working, err… optimally.

As well, it allowed 3 additional questions after feedback regarding areas of the script, areas that I was really curious to have detailed with another’s opinion to see if it would give me additional ideas for those scenes, or information that would allow me to build on or reconstruct similar scenes elsewhere in the script.

It even spit out a succinct logline that pretty much resonates with the script.

Original logline (that it never prompted for):

“Inspired by the surreal works of Lewis Carroll and L. Frank Baum: A small town girl who dreams of traveling to distant lands, suddenly finds herself on an epic quest to release her lost love from the prison of an underworld garden matrix.”

Greenlight AI Logline:

“After a young woman enters a magical realm to find her lost love, she must defeat the evil overlord who has imprisoned him and restore balance to the mystical gardens.”

So, yeah, anyway that feedback is here if anyone is curious what Greenlight AI Feedback looks like, as well as the original script if anyone’s curious as to what the AI is actually giving feedback on…

Feedback: https://www.dropbox.com/scl/fi/q11l9f7axhsx0kwu9zc29/Greenlight-AI-Feedback-The-Arpeggio-Garden.pdf?rlkey=74di5khuo9bxigdl5ja26vwcj&dl=0

Script ‘The Arpeggio Garden’: https://www.dropbox.com/scl/fi/inj7f4onvs7fhawjhwavc/The-Arpeggio-Garden.pdf?rlkey=mgajw2hcoocoh3909wt35e0o2&dl=0

Hopefully this helps, best of luck…


Thank you for sharing!

Glad we can help :)

Posted by: JackFromGreenlight, February 5th, 2024, 9:17pm; Reply: 32

Quoted from LC



Thanks, AJR!
All of that just seems really generic to me.


I'm interested in the answer to this question too.

I'm curious to know if this is going to become the way of the future e.g. getting a minimum score from AI before you can progress with certain things.

I still think the test of this would be to have AI access a really badly written script.



Thanks LC! I have answered AJR's question in another reply, but we will be sharing our industry connections very soon =)

Personally I have been in the industry for about a decade, worked on 30+ produced movies ranging from super indie ones <$100k budget to Nicolas Cage movies budgeted over $20m (I was responsible for his casting decision on that one too). Evaluating screenplays and getting feedback have always been a difficult problem for me.  I certainly hope we can make this process better and help good screenplays get discovered and produced, as well as helping existing scripts to be improved.

We have done a few bad movies for sure, I will link a blog post that has "The Room" coverage report here if you want to check it out: https://glcoverage.com/2024/01/27/what-is-script-coverage-script-coverage-examples-and-insights/

Cheers!
Posted by: PKCardinal, February 6th, 2024, 1:23pm; Reply: 33

Quoted from JackFromGreenlight


Thanks LC! I have answered AJR's question in another reply, but we will be sharing our industry connections very soon =)

Personally I have been in the industry for about a decade, worked on 30+ produced movies ranging from super indie ones <$100k budget to Nicolas Cage movies budgeted over $20m (I was responsible for his casting decision on that one too). Evaluating screenplays and getting feedback have always been a difficult problem for me.  I certainly hope we can make this process better and help good screenplays get discovered and produced, as well as helping existing scripts to be improved.



We have done a few bad movies for sure, I will link a blog post that has "The Room" coverage report here if you want to check it out: https://glcoverage.com/2024/01/27/what-is-script-coverage-script-coverage-examples-and-insights/

Cheers!


I'll say this...the AI LOVES them some Timothee Chalamet. That, or, maybe we should all be on the alert...Timothee Chalamet may actually BE an AI bot. Which, when you think about it, makes a lot of sense.



Question for Jack: I didn't see the typical PASS, CONSIDER, RECOMMEND. Is that included in the coverage?
Posted by: JackFromGreenlight, February 6th, 2024, 4:33pm; Reply: 34

Quoted from PKCardinal


I'll say this...the AI LOVES them some Timothee Chalamet. That, or, maybe we should all be on the alert...Timothee Chalamet may actually BE an AI bot. Which, when you think about it, makes a lot of sense.



Question for Jack: I didn't see the typical PASS, CONSIDER, RECOMMEND. Is that included in the coverage?


LOL re: Timothee Chalamet.

As for the Pass Consider Recommend, I also heard this from many users, so we are working on a section right now to include that in the future.  May take us a few weeks, but it will be there for sure.

Posted by: PKCardinal, February 6th, 2024, 4:48pm; Reply: 35

Quoted from JackFromGreenlight


LOL re: Timothee Chalamet.

As for the Pass Consider Recommend, I also heard this from many users, so we are working on a section right now to include that in the future.  May take us a few weeks, but it will be there for sure.



Nice. Thanks for the response!
Posted by: FrankM, February 6th, 2024, 7:02pm; Reply: 36
Thanks Jack for coming in and having this conversation.

The casting recommendations sound like a value-added feature that could help screenwriters like me who have an interest in writing, but no interest in investing the time and energy in following A-, B- and C-tier celebrities.

Other possibilities:

  • Generating comp films if it can be done with decent confidence. Probably only relevant for features.

  • Expandable explanations for why certain feedback is present. I expect this would be an extra fee, but could go a long way in building trust in the model. (AKA "Explainable AI")

  • Recommend/Consider/Pass but with an explanation that this is not some specific "industry pro" rendering an opinion. Making this expandable would be valuable as well, especially if it's not a straightforward point system.

  • Summaries about characters or pseudo-characters (narrators, MacGuffins, etc.), again expandable if that's feasible.

  • Comments on the script's structure. "Your script appears to be structured according to the Hero's Journey, but...". Again, probably only for features. The most you can say about a short is that it has a beginning, middle, and end.

I understand these are all things that are way easier to say than do... take them as idle suggestions from someone who knows a little about AI but not enough to help implement any of those ideas.
Posted by: JackFromGreenlight, February 7th, 2024, 12:28am; Reply: 37

Quoted from FrankM
Thanks Jack for coming in and having this conversation.

The casting recommendations sound like a value-added feature that could help screenwriters like me who have an interest in writing, but no interest in investing the time and energy in following A-, B- and C-tier celebrities.

Other possibilities:

  • Generating comp films if it can be done with decent confidence. Probably only relevant for features.

  • Expandable explanations for why certain feedback is present. I expect this would be an extra fee, but could go a long way in building trust in the model. (AKA "Explainable AI")

  • Recommend/Consider/Pass but with an explanation that this is not some specific "industry pro" rendering an opinion. Making this expandable would be valuable as well, especially if it's not a straightforward point system.

  • Summaries about characters or pseudo-characters (narrators, MacGuffins, etc.), again expandable if that's feasible.

  • Comments on the script's structure. "Your script appears to be structured according to the Hero's Journey, but...". Again, probably only for features. The most you can say about a short is that it has a beginning, middle, and end.

I understand these are all things that are way easier to say than do... take them as idle suggestions from someone who knows a little about AI but not enough to help implement any of those ideas.


Thanks for the feedback Frank.

We actually have most of the above functions built and some of them are accessed through the follow up questions that you can ask our A.I. reviewer.  


Print page generated: May 14th, 2024, 4:30am