Another useful use-case with Jev from @typesafeai - AI text

The clip posted with this case (hosted by the collector’s media CDN); original post on X · 4s.

Used Jev for AI text classification that came close to Pangram at 6000x lower cost and 5-10x faster, tested on a Paul Graham essay.

The original post

Another useful use-case with Jev from @typesafeai - AI text classification.

Very close to @pangram, 6000x cheaper, 5-10x faster

Tested here on a @paulg essay!

What the author linked

From the same thread

  • @Totzenberger — Classification performance is amazing. Built an AI-text detector that's 6000x cheaper than @pangram while being as good and way faster. Thanks @typesafeai

Engagement when collected

Views50.1K
Likes124
Bookmarks121
Reposts2
Replies17
Quotes3

Numbers are a snapshot taken from X when the case was added to the library (schema v1, collected 2026-09-19); they will not match today.

Where this case fits

Filed under classification & data extraction. In the pattern Jev is built for, the model answers a bounded question per step — and ordinary code acts on the answer, because the answer is already a value rather than a paragraph. Other posts in the same family are on the classification & data extraction page.

Related Jev cases

Keep browsing: all 1173 Jev cases · more from @Totzenberger · builders · what Jev is

Last updated: 2026-09-22 · sources & corrections · every card links to its author's original post