I would bring to the homepage your note about privacy.
My wife is a writer and her and her community go to great lengths to avoid having their writing being used to train models. It's a privacy thing but it's also I don't want my ideas thing.
Authors probably would make the most dodgy ai queries of just about anybody. We're often writing about deviant or criminal personalities, extreme moods or actions.
Wont the safety systems of your providers automatically save all this history indefinitely and then it will be out there forever to be used against us in some way? Eg, suppose a custody hearing or professional conduct review or a trial or even a job interview or insurance claim?
Especially if its reading and researching in the background as you go
I'm not writing a book right now, but I love this idea. In general, I think many AI tools treat writing (or designing, or coding, or...) as a necessary evil we should eliminate. So the AI tool does it for you.
Now that we're realizing the writing, coding, designing process is actually important and many of us enjoy them, these kinds of tools are great.
AI tools that work with you and augment your process, but don't replace it.
Exactly, and thank you, that's encouraging to hear. What sort of thing would you like to see in a tool like this ? I'm still actively iterating based on what people actually want.
I haven't tried the product, but a few things come to mind. I'll share them below, but just for context: I don't write books and I only write non-fiction. Just in case that changes whether I'm the target user for this.
The support I'd like depends on phases of the writing process. In the beginning, I might be open to completely reworking an angle or structure, but that kind of feedback wouldn't be helpful afterwards.
I build interactive stories for kids, where every choice changes the ending. It's like graphs where each node is a part of the story with an illustration and each 'What if...' choice is a path-connector. The map is the whole thing. The hardest part was never the text, it was seeing the threads - what is left, what connects to what and if there are no loops. A tool that shows me the map and never writes a word is exactly what I need.
I am also writing a book, and it is the same problem there - did I miss anything, did I mention that previously or it was missed?. Going to try this.
You just unlocked a key memory, Those where pretty popular in the 80's, I used to read them, the classic "You decide to go down the left path, go to page 83-2/"you decide to sleep for night, go to page 72-1" type.
They were a lot of fun, it's neat someone is still doing those :).
They reminded me a lot of MOO's which I didn't get into til years later.
I like this approach to AI tools. I expect we'll have a split where many tools will focus on completely automating and removing the humans from the process, and a minority will focus on enhancing the human and putting them in the center of the process.
Does this work for blog posts and the like?! I could see it being very useful for keeping you on track in realtime as opposed to pinging LLMs afterwards?
This is really cool, if you manage to integrate formal methods to verify the plot it would get even more interesting, I saw someone on X using Lean to do so perhaps you may want to move faster.
I really like this approach of AI being like an "exoskeleton" -- amplifying your thinking rather than replacing it.
I think we have jumped to the "switch brain off" style of AI use (unsurprisingly because it's the path of lease resistance and of most immediate progress). I really hope there's an alternative world where the technology can be used to engage your brain more than ever.
I agree here... I'm working on some inter-related spec docs and stuff, it'd be great to have like an "eye in the sky" looking for generated topics/concept maps and looking for contradictions.
Example: In DESIGN.md you said 15%/25%/50%, but in ARCHITECTURE.md you said 20%/40%/60%... this is all related to `#constants-and-limits`, click here to find more!
Example: PRINTING.md, ENCODING.md, and CAPACITY.md show significant conceptual overlap! Click here for a `git-diff` showing side-by-side-by-side paragraphs which cover `#topic1; #topic2; #topic3` for potential consolidation or refactoring!
Example: Autodetected topics: `#design; #architecture; #printing; #encoding; #capacity` from `UPPERCASE.md` filenames. Suggested topics: `#ux; #backups; #integration` from semantic analysis.
...even if you were writing a fictional book, having something like: `JOE_MAIN_CHARACTER.md; JANE_ROMANTIC_INTEREST.md; GEO_PARIS.md; TOPIC_WILL.md; GEO_NEIGHBORHOOD.md; THE_MURDER_TIMELINE.md`
These "big rocks" would manually written + managed, those topics are specifically searched/analyzed for, and if you update THE_MURDER_TIMELINE.md from "neighborhood -> joe -> jane -> paris -> will" to "joe -> neighborhood -> jane -> will -> paris", being able to cross-check or flag your own contradictions over a larger body of work would be like having a tireless editor watching over almost every keystroke!
I actually like the idea of this a great deal, Augmenting the human (insert classic "bicycle for the mind" quote) is the one thing I do like about AI.
It's also largely the way I use AI currently for development, I write the code, then I throw it at the clanker to review, it comes back, I read what it output carefully, if I agree I alter my code, if I don't I leave it out (and update errata.md to say why for the future if I strongly disagree).
It's essentially treat as a slightly smarter rubber duck but the code is still mine and I still understand what it does vs just throwing it over the fence and running.
Sounds interesting!
I do wonder whether this will become a new loophole - “I didn’t consult the AI about killing someone, I was just writing a book.” [0]
It looks interesting, but I can't pause the video/animation. I see a lot of mouse movement and things opening and closing, but it's too fast (for my old eyes, at least).
Thanks for the pointer, what they're doing is very similar. I think the difference is that I'm not avoiding AI, I'm avoiding having it write anything for the user. And yes, agreed on git: Foolscap keeps each book's history in git too. Everything should transparently belong 100% to the user.
Similar is fine. It's like jazz; let their music inspire your music. And vice versa. You'll make better music. Play for a bigger and bigger audience. Have fun.
Ooh and this one is open source, too! Thanks for sharing. This seems like it might even be useful while reading books. I have trouble keeping characters straight sometimes when there are many.
Yeah, so that can be done with foolscap too. I had previously a Labyrinth feature that could do what you just described, but I put it aside for now, in favor of a more simple system that can pick out structure in the writing without giving the user access to the internal representation. If that feature is wanted, then I can add it back in. Then, it could be used as a companion to reading or even modifying existing works of literature.
This is cool! I share the sentiment and have also actively been thinking about how AI can help us enhance skills and creativity.
It's helped me with design [1] but I've also been building tools in this vein as experiments.
[1] https://railcode.dev/blog/vibe-coded-website
Thank you, what tools have you been experimenting with ?
I made something similar at https://authrot.app/
I went to great lengths to improve the precision of scans across an entire book. You can read about it in my blog here: https://authrot.app/blog/how-authrot-reads-a-novel
I would bring to the homepage your note about privacy.
My wife is a writer and her and her community go to great lengths to avoid having their writing being used to train models. It's a privacy thing but it's also I don't want my ideas thing.
It's there now. If your wife or her community would like to try, happy to give them free access.
Authors probably would make the most dodgy ai queries of just about anybody. We're often writing about deviant or criminal personalities, extreme moods or actions.
Wont the safety systems of your providers automatically save all this history indefinitely and then it will be out there forever to be used against us in some way? Eg, suppose a custody hearing or professional conduct review or a trial or even a job interview or insurance claim?
Especially if its reading and researching in the background as you go
I'm not writing a book right now, but I love this idea. In general, I think many AI tools treat writing (or designing, or coding, or...) as a necessary evil we should eliminate. So the AI tool does it for you.
Now that we're realizing the writing, coding, designing process is actually important and many of us enjoy them, these kinds of tools are great.
AI tools that work with you and augment your process, but don't replace it.
Very much agree with this. So many of us want to remain the core driver of the creative process while benefitting from new AI/LLM tech.
It's encouraging to see tools like this keeping humans at the center of their approach
Thank you! It'll take a lot of iteration to tighten it up and get it right, but I'm glad it finally exists.
Exactly, and thank you, that's encouraging to hear. What sort of thing would you like to see in a tool like this ? I'm still actively iterating based on what people actually want.
I haven't tried the product, but a few things come to mind. I'll share them below, but just for context: I don't write books and I only write non-fiction. Just in case that changes whether I'm the target user for this.
The support I'd like depends on phases of the writing process. In the beginning, I might be open to completely reworking an angle or structure, but that kind of feedback wouldn't be helpful afterwards.
I build interactive stories for kids, where every choice changes the ending. It's like graphs where each node is a part of the story with an illustration and each 'What if...' choice is a path-connector. The map is the whole thing. The hardest part was never the text, it was seeing the threads - what is left, what connects to what and if there are no loops. A tool that shows me the map and never writes a word is exactly what I need. I am also writing a book, and it is the same problem there - did I miss anything, did I mention that previously or it was missed?. Going to try this.
You just unlocked a key memory, Those where pretty popular in the 80's, I used to read them, the classic "You decide to go down the left path, go to page 83-2/"you decide to sleep for night, go to page 72-1" type.
They were a lot of fun, it's neat someone is still doing those :).
They reminded me a lot of MOO's which I didn't get into til years later.
I like this approach to AI tools. I expect we'll have a split where many tools will focus on completely automating and removing the humans from the process, and a minority will focus on enhancing the human and putting them in the center of the process.
We need more tools of this kind.
Does this work for blog posts and the like?! I could see it being very useful for keeping you on track in realtime as opposed to pinging LLMs afterwards?
This is really cool, if you manage to integrate formal methods to verify the plot it would get even more interesting, I saw someone on X using Lean to do so perhaps you may want to move faster.
I really like this approach of AI being like an "exoskeleton" -- amplifying your thinking rather than replacing it.
I think we have jumped to the "switch brain off" style of AI use (unsurprisingly because it's the path of lease resistance and of most immediate progress). I really hope there's an alternative world where the technology can be used to engage your brain more than ever.
I’m writing a book at the moment. But not a storybook, more a teach-yourself-the-basis-of… kind of book.
Is this tool any good for these kinds of text?
I agree here... I'm working on some inter-related spec docs and stuff, it'd be great to have like an "eye in the sky" looking for generated topics/concept maps and looking for contradictions.
Example: In DESIGN.md you said 15%/25%/50%, but in ARCHITECTURE.md you said 20%/40%/60%... this is all related to `#constants-and-limits`, click here to find more!
Example: PRINTING.md, ENCODING.md, and CAPACITY.md show significant conceptual overlap! Click here for a `git-diff` showing side-by-side-by-side paragraphs which cover `#topic1; #topic2; #topic3` for potential consolidation or refactoring!
Example: Autodetected topics: `#design; #architecture; #printing; #encoding; #capacity` from `UPPERCASE.md` filenames. Suggested topics: `#ux; #backups; #integration` from semantic analysis.
...even if you were writing a fictional book, having something like: `JOE_MAIN_CHARACTER.md; JANE_ROMANTIC_INTEREST.md; GEO_PARIS.md; TOPIC_WILL.md; GEO_NEIGHBORHOOD.md; THE_MURDER_TIMELINE.md`
These "big rocks" would manually written + managed, those topics are specifically searched/analyzed for, and if you update THE_MURDER_TIMELINE.md from "neighborhood -> joe -> jane -> paris -> will" to "joe -> neighborhood -> jane -> will -> paris", being able to cross-check or flag your own contradictions over a larger body of work would be like having a tireless editor watching over almost every keystroke!
I actually like the idea of this a great deal, Augmenting the human (insert classic "bicycle for the mind" quote) is the one thing I do like about AI.
It's also largely the way I use AI currently for development, I write the code, then I throw it at the clanker to review, it comes back, I read what it output carefully, if I agree I alter my code, if I don't I leave it out (and update errata.md to say why for the future if I strongly disagree).
It's essentially treat as a slightly smarter rubber duck but the code is still mine and I still understand what it does vs just throwing it over the fence and running.
Sounds interesting! I do wonder whether this will become a new loophole - “I didn’t consult the AI about killing someone, I was just writing a book.” [0]
[0] https://www.cbs17.com/news/ap-prosecutor-alleges-ex-nfl-play...
the hero page title ("Your book, alive as you write it.") reads as a claudism
It looks interesting, but I can't pause the video/animation. I see a lot of mouse movement and things opening and closing, but it's too fast (for my old eyes, at least).
Thanks a bunch for your feedback.
Hey, you should be able to pause and unpause it now.
Yes, thank you very much.
I wonder how different this is from cursor in ask mode
The mobile site just shows a giant image that I can’t open and the quick text sell before linking to plans
The page is deliberately short, but I'm taking note that it feels off on mobile.
Makes sense, yeah I can't even see the image on mobile (or maybe it's supposed to be a video?)
this is great, love seeing apps like this! also Foolscap a great name. (Fleshnote not so much lol)
thank you! :)
Another (vibed/pre-release) app in this space is Fleshnote[0]. It's a large install, but has a similar write first, note second approach.
The pentimento feature ('git for prose') is likely something we'll start seeing more in other authoring environments going ahead.
[0]: https://fleshnote.org/
Hadn't seen fleshnote! My friend Bobby also made Marginalia[0] which is somewhat similar
[0]:https://marginalia.bobbby.online/
Thanks for the pointer, what they're doing is very similar. I think the difference is that I'm not avoiding AI, I'm avoiding having it write anything for the user. And yes, agreed on git: Foolscap keeps each book's history in git too. Everything should transparently belong 100% to the user.
Similar is fine. It's like jazz; let their music inspire your music. And vice versa. You'll make better music. Play for a bigger and bigger audience. Have fun.
I'm surprised by how welcoming, kind, and supportive this community is, and love the jazz comparison.
Ooh and this one is open source, too! Thanks for sharing. This seems like it might even be useful while reading books. I have trouble keeping characters straight sometimes when there are many.
Yeah, so that can be done with foolscap too. I had previously a Labyrinth feature that could do what you just described, but I put it aside for now, in favor of a more simple system that can pick out structure in the writing without giving the user access to the internal representation. If that feature is wanted, then I can add it back in. Then, it could be used as a companion to reading or even modifying existing works of literature.
good
thanks!