Small decisions. Interesting possibilities.Submit contentSubmit

100,000 viral posts in 20.4 seconds

I just built a Jev X Viral Post Analyser. 100,000 viral X posts. 20.4 seconds. $0.67. Claude Opus 5, same corpus, same clock, got through 214 posts and spent $0.98. per post that is ~680x cheaper the full Opus pass would have run $458. viral analysis is the perfect Jev job. • it is not writing, it is 14 yes/no calls…

Added to Jevfast

How it uses Jev

For each X post, Jev answers 14 yes-or-no questions, including whether the hook opens a loop, a number appears in the first line, and proof is real or claimed. The system aggregates classifications across the corpus to analyze patterns among viral posts.

App workflow

  1. Load the corpus

    The analyzer processes a corpus of 100,000 X posts gathered through X APIs.

  2. Judge each post

    Jev answers 14 yes-or-no questions about each post; the post gives examples about hooks, numbers, and proof.

  3. Aggregate classifications

    The analyzer counts patterns across the corpus and compares them with the reported top one percent.

  4. Inspect results

    The demonstration shows a post alongside Jev's typed answers and confidence scores.

Why it is interesting

The analysis is decomposed into repeated classification calls rather than prose generation, making a large corpus pass practical and allowing the creator to compare patterns across posts.