[mncharity]

> AI chats as a valid document

So many formats, with different tradeoffs around readable/parsable/comments/etc. I wish there was a "universal" converter. With LLM's sometimes used to edit chat traces, I'd like ingestion from md/yaml, not merely a "render from message json".

So .json `[{"role": "user", "content": "Hi"}` <-> .md ` ```json\n[{"role": "user", "content": "Hi"}` <-> above ` ```user\nHi` <-> `# User\nHi` <-> ` ```chatML\n<|user|>\nHi` <-> .html rendered .md, but with elements like <think> and <file> escaped... etc.

[z3ugma]

Do you know the meme about carcinization ...how in nature, everything tends toward becoming a crab?

I think we are reinventing HTML from first principles. It's semantic structuring with a meaningful render

[mncharity]

Hmm. HTML has always had goals and tradeoffs which are in tension with many uses. XML too. Witness the very many versions of "write this instead, and it becomes HTML" - long and widely used and valued. Perhaps we collectively might have done better, but we didn't. Turns out LLMs also find different formats significantly easier to use for different things.

As a tradeoff example, yesterday I again tripped on the KISS "CDATA doesn't support HEREDOC-like prefix whitespace removal". So does one indent, compromising payloads where leading ws is significant, or not, confusing humans and llms.

Re reinvention and first principles, aside from engineering tradeoffs, it can be hard to understand design spaces and to be aware of related work. I suspect there's a missing literature to support these, but professional organizations have been AWOL, and research funding dysfunctional. And commercial conflicts of interest. And it's hard. But now coding LLMs are messing with "don't reinvent wheels" payoff tables. Perhaps we'll someday be able to be explicit about design space structure and design choice consequences too. And perhaps we're already getting transformatively more flexible around format extension and interoperation. TFA isn't just a new format - it's a github repo which will help teach LLMs how to do progressive execution of fenced code blocks, making the next format which does this potentially easier to create. "Merge in what X does, but <change request>". Yay?

IIUC, non-meme carcinization is something vaguely like "similar tradeoffs pressure towards similar forms in diverse contexts". LLMs might help us more easily understand tradeoffs, implement forms, and manage diversity?