deftio

Definitely sympathetic to their policy, but AI tooling and quality are changing quite fast. In a year I'd expect a modification of this as AI agents get better in virtually every possible way.

Anybody remember corewar, where each player wrote an adversarial programs in redcode?

Wow. Where was this in the 90s when I "needed" it.

Is there a console version?

Totally agree.

Agree.. 68k assembly was dreamy compared to 80x86..

Wow.... I remember writing 8086 assembly on MASM and another assembler I've forgotten the name of, and then also doing inline ASM in Turbo C++

The segment thing and the convoluted different pointer math caused real gymnastics if you ever had data bigger than 64k... such as images.

I always thought of the segments as windows of 64k but moving between those windows, esp with the limited register set, required some real mental gymnastics.

There is some base level of intelligence any model needs to be useful, even in narrow tasks.

Could you teach a 5 year old to drive a car? A 10 year old? A 12 year old? To drive a car requires being able to read, to have judgement about ice or rainy conditions, to anticipate a child running after a ball. By the time a human in in their mid teens they have acquired the base knowledge...

Small models need to have enough base knowledge to be able to be good enough -- even in a seemingly narrow regime. Where is that? Obviously they don't need all the obscure knowledge of a frontier model but there is some base level which is probably more than it would first seem.

As smaller models become more capable I suspect we will see a reset in token economics.

How long has this been running?

In word.. the asks need to separated from execution. Labeling or tagging the prompt itself is a dead end.

It seems useful but then we have to manage similar metadata in multiple places, so hygiene around consistency becomes important

Truly agree with the framing of buy vs build.

Also, some software businesses use a ton of aggregated or hard to get data which needs to be synthesized and that doesn't go away even if the llm driven coding is cheap.

Hi HN-

This past year I've built and maintained Quikdown, a bidirectional markdown parser and companion editor in pure js, with batteries included fences for rendering rich content.

Try it live: https://deftio.github.io/quikdown/pages/edit/

The motivation was working with many different LLM frameworks and wanting to test tool calling and collaborative editing. Often I just wanted a pretty final output with rich support for diagrams, math, or other rendered content but, keep it editable. So a user (often me) could just work on the final (rendered) output while the LLM could see/seek/update/edit just using markdown under the covers. Quikdown editor supports md/split/rendered output and can run headless so you can bring your own UI. MCP support is included as well.

The Quikdown parser has zero dependencies and is based on regex and outputs HTML with built-in tags for triggering plugins for fences (like Mermaid, Vega-lite, code syntax, music and many more). A separate set of attributes allow tracking of bidirectional content so a user can edit markdown tables, code rendered in highlightjs and many other types in the rendered view. For complex rendered types (like Mermaid or STL) bidirectional support is not included but if you want to take that on there are hooks to support your own efforts.

While the parser has no dependencies , the editor lazy-loads appropriate libraries for rendering rich content. Supported fences include: Mermaid, MathJax, SVG, CSV/TSV/PSV tables, GeoJSON with live leaflet based pan-and-zoom, Sheet music (via ABC.js), Vega/Vegalite-charts, STL (via threejs), code highlighting (via highlightjs).

Also included is programmatic undo/redo - so if you are making a closed loop with another output service (LLM or some process) you can roll back content changes that were not desired.

All inline HTML is escaped by default - no eval() or other unsafe raw parsing of content is allowed and URL sanitization blocks script based urls. However if you are using the editor the plugins which render rich content are left to handle that content on their own and are hence "trusted".

Quikdown intentionally doesn't cover all of Commonmark compatibility - if you find some portion of the spec isn't covered that you need raise an issue or make a PR and I'll take a look.

A standalone "air-gapped" build is also provided so you can use quikdown locally with zero cloud support. The standalone build is about 8MB so not recommended for use in online applications.

Longer write-up: https://deftio.github.io/quikdown/pages/blog/