I work with AI tools often and I find myself constantly swapping between file types to navigate different sites and use cases. I built anydoc — I imagined a universal document format drive layer that would allow me to essentially have a file that is many different file types at once. CSV for organizing, markdown for feeding into LLMs, HTML for fast sharing... so here it is and I am working on making it better all of the time. Just shipped an update that makes the most relevant format types available faster on a document upload @boshjerns on X

You might not want to use https://anydocai.com/result/<incremental number> for URLs like that. Anyone can enumerate the ~300 files from the home page and look at what others have uploaded.

That said, the website doesn't seem to work anymore. It just errors out.

I think calling it a "drive" will confuse a lot of people. I expected a device driver, and not technical people have no idea of drives, they just have documents and photos.

I tried with a text file

  X Y
  1 2
  3 4

and for some reason the convert version has 1 2 3 4 in the same row.

I thought this was something like a FUSE driver that would on-the-fly generate any file you tried to read, with some consistency. Like if you open stories/zombie-party.txt it will have some generative network make it, and cache it. If you later ask for stories/zombie-party.odt it can just do a conversion.

I vibe-coded a demo of such a thing, with the idea of making game assets like textures/outdoor/wall.jpg etc. You can do it easily enough, but you need to be patient, and not particularly discerning.

I got "No video with supported format and MIME type found." in the How It Works section.

It's a fancy file format conversion utility.

Am I missing something?

So I can have my exe convert into a shapefile and an mp3?

AI as a use case doesn’t make sense to me.

You’re using AI to create a transpilation of whatever modality. It’s a wasted step if the purpose is to feed back into AI.

Back in the day there were a bunch of `x2y` programs[1], like html2pdf, xls2csv, rst2odt, jpg2png, png2jpg, etc...

You could imagine something like `any2zip`, or `any2tgz` or `iso2mp4` or something.

It seems like there could/should be some sort of virtual filesystem where you could say "cat inventory.xls.csv", or "wine.exe excel.exe inventory.csv.xls" (please bear with me on these examples). Effectively "$BLOB.format.format", where "." becomes a sort of "convert to this $TYPE".

Imagine being able to say:

    `echo "# Hello\n\n * World" > README.md ; cat README.md.html"`
    (effectively invoking `md2html`)
    
    `printer README.md.html.pdf`
    (eg: `cat README.md | md2html | html2pdf | printer`)

...if you requested `README.md.pdf`, maybe it could intuit the intermediate `md2html2pdf` (HTML) portion?

I really wish local linux filesystems (for end-users) would at least match Apple's capabilities. eg: `$RECENT`, spotlight, auto-OCR. We've really regressed since the era of `locate`, but I'd _LOVE_ some sort of modern equivalent.

Imagine: `inotify`, `auditd`, just anything that can avoid full-disk scans during "normal end user" daily operation... wired up to `llm-summary $FILE >> sqlite.db ; `llava-describe $IMAGE >> sqlite.db ; etc...`

For bonus points, catch anything missed with some sort of full daily/weekly backup operation. We're on the cusp of a much more intimate "partnership" with the compute boxes underneath our desks, but so much is getting sucked into the void of "the network is the computer".

[1]: compgen -c | grep 2 | grep -v '2$' | grep -v '\.2' | grep -v '2\.'

[2]: https://en.wikipedia.org/wiki/Locate_(Unix)

I like the idea if it was deterministic. So if there are standard ways to convert to/from document types, like Pandoc, being able to write to any one of them and have it update the rest would be interesting.

I hate it if it's built with "AI". Can't imagine a use case for this apart from just shit you don't care about. Why would I be hoarding data I don't care about?

So it turns one file into many? Or is it actually one file that is simultaneously a valid HTML document and PNG?

Wouldn't this make every file a lot bigger?

the page is really laggy on Edge, kills any interest in wanting to explore more (strangely, it's much snappier on Chrome)

Could have called it quantumdoc

Imagine no file types

♪ It's easy if you try No hell below us Above us only sky Imagine all the people Visualize whirled peas Ah ah ah oooo!

You may say I'm a dreamer...

Now make it an HTTP API where content negotiation always succeeds

[flagged]

[flagged]

i ve read the title 5 times, and can't make sense of it. Is this even valid English ?