jev.directory
Systems
noulchoiceClassificationData

I gave Jev 3,282 of my X posts across 100M views and asked it to find what ac…

jev.directory1 like

Ian Nuttall ran 3,282 of his own X posts (100M views) through Jev to find what actually drives growth.

Each post was asked eight questions — its topic, its hook, its tone, whether it teaches the reader something — turning a pile of unstructured posts into a table you can group and rank. The finding that came out: how-to posts carry a 150 median likes.

The point is the cost profile. 4,252,330 tokens, $0.1282, 8m34s for the whole corpus. Classification at that price is what makes asking eight questions of every row reasonable instead of a budget decision.

I gave Jev 3,282 of my X posts across 100M views and asked it to find what actually works for growth. 4,252,330 tokens $0.1282 for the full 8m 34s run! Each post got 8 questions about the topic, hook, tone, whether it teaches something, etc. How-to posts got 150 median likes