HN user

FailMore

1,760 karma

hi [attttty] sdocs [dottttt] dev

Posts218
Comments399
View on HN
news.ycombinator.com 2mo ago

Ask HN: How do word docs, slides, excel, and PDFs generate value?

FailMore
6pts10
sdocs.dev 2mo ago

After extensive work with agents, the non-technical sentence is the shape I see

FailMore
3pts0
sdocs.dev 2mo ago

After extensive work with agents, the non-technical sentence is the shape I see

FailMore
3pts0
sdocs.dev 2mo ago

Show HN: (Update) Mermaid Diagrams in SmallDocs

FailMore
1pts0
sdocs.dev 2mo ago

The surprisingly complex journey to text-selectable client-side generated PDFs

FailMore
3pts0
sdocs.dev 2mo ago

The surprisingly complex journey to text-selectable client-side generated PDFs

FailMore
86pts62
sdocs.dev 2mo ago

Show HN: Proving sdocs.dev is running the public code

FailMore
2pts0
sdocs.dev 3mo ago

Proving sdocs.dev is running the public code

FailMore
2pts0
news.ycombinator.com 3mo ago

Ask HN: Do you comment on a code/Markdown files, then get your agent to reread?

FailMore
2pts2
news.ycombinator.com 3mo ago

Ask HN: Is your Claude pausing more frequently?

FailMore
1pts1
sdocs.dev 3mo ago

Show HN: SDocs – A CLI and webapp for private Markdown reading and sharing

FailMore
1pts0
news.ycombinator.com 3mo ago

Show HN: SmallDocs – Markdown without the frustrations

FailMore
92pts50
www.theguardian.com 4mo ago

Surge in giant sinkholes threatens Turkey's farmers

FailMore
11pts0
news.ycombinator.com 5mo ago

Show HN: Rebrain.gg – Doom learn, don't doom scroll

FailMore
111pts53
news.ycombinator.com 5mo ago

Ask HN: Have you started to use "->" when you type after working with LLMs?

FailMore
2pts3
salesfeed.xyz 9mo ago

Show HN: salesfeed.xyz – Track everything about your sales targets

FailMore
1pts0
news.ycombinator.com 11mo ago

Ask HN: How are you using LLMs?

FailMore
3pts6
news.ycombinator.com 1y ago

Ask HN: What are the most autonomous AI agents you know of?

FailMore
1pts1
requirement5.com 1y ago

Show HN: Generate virtual shiny cards with different rarity levels

FailMore
2pts1
flopsy.io 1y ago

Show HN: Flopsy, a [paid] tool to teach poker players about hand combinations

FailMore
1pts0
news.ycombinator.com 3y ago

Ask HN: How good is Google's Bard?

FailMore
3pts3
news.ycombinator.com 3y ago

Ask HN: How good is Google's Bard?

FailMore
14pts4
www.taaalk.co 3y ago

Show HN: My Conversational Social Network

FailMore
14pts4
psychotherapist.substack.com 3y ago

Mental Illness Is in Your Head

FailMore
1pts1
psychotherapist.substack.com 3y ago

Mental Illness Is in Your Head

FailMore
5pts0
news.ycombinator.com 3y ago

Ask HN: Would you like to make an AI artist with me?

FailMore
2pts1
www.taaalk.co 4y ago

Show HN: Taaalk – Try out my side project (invite code 848581320)

FailMore
1pts0
www.taaalk.co 4y ago

Show HN: Try out my side project Taaalk

FailMore
2pts2
taaalk.co 4y ago

Taaalk

FailMore
4pts2
psyarxiv.com 4y ago

Dreaming Is the Inverse of Anxious Mind-Wandering

FailMore
1pts0

I've been building SmallDocs [1], a fairly fully functional office suite (text, formatting, presentations, spreadsheets) which is based in markdown (and mainly written by agents).

Given my experience building this, I think the idea of "a truly independent document":

one that displays identically on any system, in any country, for any user, regardless of the software used

Will be very difficult to achieve in practice.

Building software is an expression of opinions. And one of the main drivers of building an app is to innovate or improve the user experience vs. what exists today. These things combine to result in new features, and new features breaks the open standard.

If I wanted to build a new Excel, I might want to add something to spreadsheets which a basic open source reader cannot, or even Excel itself, might not be able to handle.

With SmallDocs, I built on the standard rendering of markdown, but then added a bunch of properties which traditional markdown renders would ignore.

For example, styles front matter:

  ---
  styles:
    fontFamily: Lora
    baseFontSize: 17
    h1: { fontSize: 2.3, fontWeight: 700 }
    p: { lineHeight: 1.9, marginBottom: 1.2 }
    ...
  ---
Which means you can create colorful files like: https://smalldocs.org/s/v_CHCaQHdGNVlsQtk6skEY#k=ZajP0oeiW86...

And slide blocks like:

  ~~~slide
  grid 100 56.25 bg=#0b1220
  r 6 9 82 4 text=caption color=#fbbf24 align=left | LAUNCH   REVIEW  -  Q2 2026
  r 6 18 84 16 text=title color=#f8fafc align=left | Atlas 2.0 shipped to every customer
  r 6 37 78 6 text=subtitle color=#94a3b8 align=left | What changed, what it cost, and what we learned
  l 6 47 24 47 stroke=#fbbf24 strokeWidth=0.2
  ~~~
Which means you can generate slides like: https://smalldocs.org/s/EKnIk-YdUBZeDA9yQs97mh#k=Eo-p46k-k6Q...

All this means SmallDocs markdown files only render correctly through our rendering engine - but this enables me to add something new to an existing document format.

[1] https://smalldocs.com; https://github.com/espressoplease/smalldocs

Yes, LLMs are way to literal - it is a problem.

Claude can right great code, but it’ll throw comments into the code about why we chose this approach instead of the random one I discussed with it - when the comment is of no use to a future developer.

It points at some sort of theory of mind problem in LLMs imo.

The charts are very nice, and I think the visualisation layer for LLMs is a very interesting problem.

I’ve been building https://smalldocs.org for this exact reason. It’s an office suite for AI agents - but my main use case is giving a cli based LLM the canvas to express itself - charts, mermaid diagrams, etc. I’ve extended it a bit further to be a format for all types of work so the agent can embed slides and spreadsheets in a document.

Sample document: https://smalldocs.org/blogs/what-is-a-smalldoc

Source: https://github.com/espressoplease/smalldocs

Hey, I'm building something a bit like that - please checkout https://smalldocs.org if you have time.

I say it’s as if “Claude Code & Microsoft Office had a baby...”

Code available: https://github.com/espressoplease/smalldocs

Discord: https://discord.gg/txjATTsDaq

Sample document: https://smalldocs.org/blogs/what-is-a-smalldoc

Invoked via Claude Code by saying stuff like: “sdoc me the plan for this feature”, or “dig into our logs and sdoc me a report on our latency"

I posted the same thing below, but I’m open for feedback on the license. I’ve put a lot of work in and I think there is a commercial pathway forward for the product. I don’t want to let someone else - who might be more experienced re commercialisation - take everything I’ve done and build a business with it (I’d really like to do that myself), so wasn’t sure what license to use as MIT didn’t feel right to me at the moment. But open for feedback/maybe I’m being too short sighted…

I’m open for feedback on the license. As you say/notice, I’ve put a lot of work in and I think there is a commercial pathway forward for the product. I don’t want to let someone else - who might be more experienced - take everything I’ve done and build a business with it (I’d really like to do that myself), so wasn’t sure what license to use as MIT didn’t feel right to me at the moment. But open for feedback/maybe I’m being too short sighted…

I went in the opposite direction and built https://smalldocs.org/, which is an office suite AI agents (and humans - including SWEs!) like to use.

I say it’s as if “Claude Code & Microsoft Office had a baby...”

Code available: https://github.com/espressoplease/smalldocs

Discord: https://discord.gg/txjATTsDaq

Sample document: https://smalldocs.org/blogs/what-is-a-smalldoc

Invoked via Claude Code by saying stuff like: “sdoc me the plan for this feature”, or “dig into our logs and sdoc me a report on our latency”

I think this is a very interesting concept/question. I feel like programming is more about shapes than anything else… but they seem to have mastered that fairly easily… but I totally get your point!

I built https://sdocs.dev and use it daily. It’s a CLI-driven markdown reader which (privately) renders Markdown in the browser.

When you install the CLI, it (with your permission) asks to update your base agent prompt files (e.g. `~/.codex/AGENTS.md`, or `~/.Claude/CLAUDE.md`) with info about how to use the tool.

This means all your agent chats know about SDocs, and it’s nearly always your agent which invokes the tool: “Hey Claude, sdoc me a list of all my open MRs”, etc.

I did a ShowHN about it here: https://news.ycombinator.com/item?id=47777633