What's preventing browsers from rendering a common subset of markdown without the need for browser extensions, with fallback to the current default of plaintext if parsing fails? LLM output can be copy-pasted for rendering by chat messengers and notetaking apps (e.g. DevonThink). If LLM markdown output continues to proliferate, does it become the defacto common-by-volume subset of Markdown, which browsers could standardize and render?

▲

xigoi 20 hours ago | parent [-]

There is no such thing as a common subset of Markdown. Even basic things are rendered inconsistently by different implementations. If browsers decided to add Markdown support, this would lead to another “works only in Internet Explorer” situation.

▲

walterbell 11 hours ago | parent [-]

> There is no such thing as a common subset of Markdown.

That was true before the widespread use of generative AI. LLM-generated markdown could _become_ the most common subset of Markdown, since machines can generate Markdown faster than humans.

▲

xigoi 10 hours ago | parent [-]

“LLM generated Markdown” is not a coherent description of a language. LLMs can generate anything they have seen in their training data, which includes many incompatible dialects of Markdown.

▲

walterbell 10 hours ago | parent [-]

Major LLMs (e.g. ChatGPT) have a copy button for their output, yielding markdown that is already being consistently rendered by other apps, reflecting what was consistently rendered as HTML. Presumably LLM vendors have built a deterministic way of generating spec-compliant HTML and their well-defined dialect of Markdown, otherwise their chat UI output would not render consistently.

	▲	xigoi 9 hours ago \| parent [-]
		I have certainly seen LLMs generate broken Markdown, so it’s presumably a “hope it works” thing.