top of page

Forum Comments

Problem with sync
In Shot Designer
Chronological timeline and flashbacks/flashforwards
In Causality Story Sequencer
Per Holmes
May 15, 2023
Hi, There's some of this that you already have. Since research is ordered any way you want, it's no problem to put a storyline in chronological order by simply arranging the beats in a folder that way, but then actually deliver them in a completely different order when you drop them into the whiteboard. I know it's not a timeline with specific times for when that matters. But it does encapsulate the concept of a series of events as they happened being different from the order they're delivered in. We are playing with the concept of beats having a chronological time where they happen, but we're not sold on this just being a timeline. Yes, if you're doing the exact sinking of the Titanic, maybe it matters. But if you're doing Back To The Future, it's more that a bunch of beats happen in the afternoon, and a bunch of other beats happen later in the afternoon. So we're interested in being able to paint with a broader brush, so you're not tasked with babysitting the exact time each single beats happens, and constantly maintaining such a detail timeline, when the only thing you really care about is that these 40 beats happen Wednesday afternoon in that order. Our main reason for this feature would actually be to make a graph we've tentatively called Time Zones, where one time zone is present day Wednesday to Friday, and another time zone will be The Murder in 1858. The graph would be one of the many graphs in the timeline, and would help you understand how you're narratively jumping backwards and forwards in time, and understanding how you spend your time in present day or in 1858. It would be less clear about the exact order each individual event is delivered in, because the goal is more to get an overall sense of the flow of time in your story. In terms of having a second chronological timeline, we'd probably do that as well, although it wouldn't just be a single real-world timeline. Rather, it would be multiple timelines, each represent a specific section of time. A time travel story with a moment repeating would also make a separate time zone for each parallel version of the same event, so that they can turn out differently. Each would be a section of time that we're choosing to treat as an item. The problem with a chronological timeline is as I said that it forces you to make a decision about every single beat even when you only care in broad strokes, which I think is the primary use case. Without some new invention, we'd be forcing people into a lot of babysitting, not just once, but every single time they add events. The good use case for a chronological timeline is something where the exact chronology matters. But I'd venture to say that the same thing is a frustrating feature for more garden-variety storytelling. A feature set would have to be invented to only have granularity if you absolutely care about it. We would not want most users to spend a lot of time creating underlying timelines. But point is, this has been thought about long and hard, and we're still not satisfied we have the right solution. I don't love how this is done in the other apps you mention, and we'd like to try to crack what your true cognitive benefit is, and then work towards giving you a sense of insight for each use case. There are so, so many features that look good on paper but then turn out to not really give you the mental pop you thought it would. We're being careful with this, because it's an invasive feature, and once you release it, you can't go back, even if it's wrong. But the hold up for these kinds of features right now is that we have our hands massively full with sync/collaboration, emotion tracking, some AI where appropriate, and mobile apps.
1
1
3.2.4 : AI? Oh come on...
In Causality Story Sequencer
Per Holmes
May 11, 2023
No it's not. You're conflating some highly different concepts. Generative AI will not for a long time write screenplays, although Causality is able to do a lot better at writing scenes because we know a lot more about the story, so we can write a first garbage scene that'll get you past the blank page, and occasionally provide good ideas. Given the right context provided, we've had it write scenes that we had to agree were not totally bad. But it's only because you've already spent a lot of time explaining the story in terms of tags, synopsis etc, and it just fleshes out half a page of what is your story. Still, no one is imagining that a single word of what is generated will make it to any final screenplay. Subtlety is utterly lost on AI. But the most natural fit for large language models is natural language processing, and Causality already does a spectacular job at writing beat titles and synopsis based on what you've written. I've basically stopped writing summaries myself, because the summaries written by Causality are genuinely good. The change location feature also works remarkably well, and is again a natural fit. It'll change a scene in a car to a scene in a diner, making mostly the right changes. The novel to screenplay and screenplay to novel also works remarkably well. We have a person who's adapting a novel to a screenplay, and it turns out that most of the work is a language conversion the AI does very well. You convert a beat, and then do an immediate human rewrite. It just shovels some of the sand for you, and it does it well. Where it breaks down is around emotions, because everything the AI does is cartoony. If you ask it to make a character gradually more angry during a scene, it'll just start adding "(angry)" parentheticals. And in general large language models do a poor job at rewriting whole text, because it's bad a preserving the existing text. We're finding greater success processing each paragraph separately, where we're able to do more subtle prompts, because we don't have to preserve the scene around it. Then we start to be able to increase or decrease a certain emotion, and the result isn't bad. But it still needs immediate human editing, and emotional changes are the lowest on the list, and not a good job for AI. We're mostly interested in AI to do the brunt work of language processing. And then also having the AI write garbage drafts of scenes based on your descriptions and place in the story arcs, is extremely helpful. Writer's block is about wanting the first attempt to be perfect, but with a bad draft already on the page and burning your eyeballs, you're motivated and confident you can do better. You can also use AI drafts like a Tarot deck, to give you oddball ideas. So don't be so quick to dismiss. It doesn't appreciate many important differences. AI isn't one thing. We can all agree that generative AI writing is crap, and will be for a very long time. But natural language processing is real, and AI does a far better job at it than the previous algorithmic approaches of the last 50 years, well enough that you can have a personal writer's assistant to do some brunt work that's not interesting or creative.
0
0
Directors view upside down.
In Shot Designer
Per Holmes

Per Holmes

Admin
More actions
bottom of page