Candor

What this is

Arc Codex is a collection, not a curator.

It watches the infosphere and writes down what it sees. It measures everything it can measure — readability, tone, named entities, signs of AI authorship, and a set of rhetorical manipulation patterns — and it attaches those measurements to what you're reading. Then it gets out of the way.

The feed is chronological. Newest first, the same for everyone, the same collection in the same order — modulo private posts that owners see in their own feed. There is no algorithm deciding what you should see, no personalization, no engagement ranking, no “for you.” Two people loading Arc Codex see the same public collection in the same order. The only things that change what you see are filters you choose.

Measure, don't judge

Arc Codex scores things. Every article carries a readability grade, a sentiment reading, an AI-authorship assessment, and flags for any of 48 manipulation patterns it detects.

Here is the rule those scores live under:

They annotate. They do not gate.

A score tells you something about what you're reading. It never decides whether you get to read it, or where it ranks. A manipulation flag doesn't bury an article — it labels it, in the open, and lets you judge. We don't hide the propaganda; we point at the technique and let you see it working. An article flagged as possibly AI-written still publishes, with the flag visible. A grim, hostile, or unflattering piece sits in the feed next to a cheerful one, in the order it arrived, because a collection doesn't rank its shelves by mood.

There's a built-in dissent, too. Every published article carries a Counter-Analyst note — a standing devil's advocate that argues with Arc Codex's own read, on everything. The system disagrees with itself in front of you, on purpose.

The exceptions, named out loud

Two places don't follow “measure, don't judge.” We'd rather tell you than have you find them.

• I · Comments — Moderated for Hostility

  Comments are moderated for hostility. A comment scoring past a high threshold for slurs, threats, or overt aggression is rejected. The line is set to catch abuse, not disagreement — sharp criticism, theological argument, and unhappy dissent are meant to pass, and borderline cases are kept. It’s the one place a tone measurement acts as a gate, and it acts only on comments, never on articles.

• II · The Optional Email Digest — Ranked

  The optional email digest is ranked. If you subscribe to the daily email, the handful of pieces it sends are chosen by readability score, not recency — a deliberate lean toward denser, more substantial writing. The main feed isn’t touched by this; it stays chronological. The ranking only shapes the opt-in email.

That's the complete list. If we ever add another, it goes here.

Don't trust us — read the code

The strongest thing we can say about any of this isn't a promise. It's that the whole system is open source.

Every threshold on this page is a line of code you can read. Disagree with where the comment moderation sits? It's a number in a file; change it. Think the email shouldn't rank at all? Delete the sort. Want a fork that gates on something we'd never gate on, for your own private deployment? It's yours to build.

A system that quietly distorts what you see has to be opaque to do it. This one isn't. You don't have to believe we're neutral — you can verify it, and you can override it.

That's the whole idea. A collection you can audit, running in the open, that shows you what it sees and trusts you to make up your own mind.