Unslop Day

How it works

One issue a day, at 07:30. Below is what the system does before that.

  1. 1
    Collectabout 40 sources
  2. 2
    Filterno rumours, no ads
  3. 3
    Checkevery link opened
  4. 4
    Writenumbers as published
  5. 5
    Podcastthe issue read out
  6. 6
    Publishat 07:30
One issue, from the walk over the sources to publication at 07:30.

The digest does not retell a feed. Of everything that went past the sources in a day, a few topics make the issue: the ones with a primary source under them that change something in practice.

Who runs this

I run the digest, Vadim Ilchenko. I pick the sources myself, and the six steps below run every morning in a system I built.

  1. 01

    Collect

    The system walks X lists, RSS, Hacker News, lab blogs (OpenAI, Anthropic, DeepMind) and newsletters. About 40 sources per run, and I pick what is on that list.

  2. 02

    Filter

    Rumours, reposts and marketing are dropped by rules I set. What stays has a primary source under it: a lab post, a paper, a repository, a document.

  3. 03

    Check

    The system opens every link and compares it with the text of the issue. A claim that does not match what the source says never reaches the issue.

  4. 04

    Write

    The issue is written in Ukrainian and translated into English. Numbers and links stay as the source has them, with no rounding and no retelling.

  5. 05

    Podcast

    The finished text becomes a podcast, the same selection for listening instead of reading.

  6. 06

    Publish

    At 07:30 the issue, the PDF and the podcast appear on the site.

Sources

The list I picked, and what step 1 walks. It is open: every topic in an issue can be checked against where it came from.

The rule I set: a claim goes into an issue when a primary source backs it, or when two independent sources confirm it. One post is not enough; where there is a single source, the issue says so.

Suggest a source

An X account, a blog, an RSS feed, a newsletter.

A URL, or an X handle like @karpathy.

What does not make an issue

Formats

Every issue is text on the site, a PDF with clickable sources and a podcast. Links in the text go to the primary source. Any issue in the archive can be checked on that.

All issues