Analyzing 18,000 tweets for viral patterns with Jev in 31 seconds
The author split viral-post analysis into 14 yes/no checks per post, ran 18,000 tweets through Jev in 31 seconds for 71 cents, and shared findings on which hook types perform best.
i built a Jev tool that reverse-engineered what actually goes viral in ai twitter. 18,000 posts. 31 seconds. 71 cents. the same run on opus 5 crawled through a few hundred and cost me ~$400. per post that is hundreds of times cheaper. viral analysis is the perfect Jev job. it is not writing, it is 14 yes/no calls per post: > does the hook open a loop > is there a real number in the first line > is the proof shown or just claimed classification, not prose. what it found: > superlative and absurd-number hooks: ~2x more likely to break out > contrarian takes: well above baseline > "i built this" tool drops: consistently over baseline > numbered listicles, the thing everyone posts: below baseline the most-used hook is the least viral one. a censored swear in the first line beat the clean version almost every time. what you're watching: left is the post, right is Jev answering 14 questions about it live, each with a confidence score. the run ends the second it clears all 18k. dropping the full breakdown as an article.