@Nils_Reimers does the SBERT embedding based few-shot

@jsmarr Joseph Smarr · Sep 19, 2026 · case #197323 · listed via Jev Hub

Asked whether modern SBERT few-shot classifiers now match Jev or whether Jev is still a step beyond them.

The original post

Maybe? @Nils_Reimers does the SBERT embedding based few-shot classifier stuff we jammed on in 2022 "just work" amazingly now with more modern models / better embeddings, or is @typesafeai jev still a leap forward beyond that?

Engagement when collected

Likes0

Bookmarks0

Reposts0

Replies0

Quotes0

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.

🗂️ Classification & data extraction