My favorite Jev hypothesis: BERT’s revenge.

@perelman020306 Perelman · Sep 19, 2026 · case #504401 · listed via Jev Hub

Hypothesized Jev fills masked schema slots in one bidirectional pass, with frontier LLMs teaching the decisions.

The original post

My favorite Jev hypothesis: BERT’s revenge. Instead of autoregressively generating JSON: build the schema → mask the values → fill every slot in one bidirectional forward pass. Then use frontier LLMs + RLCD to teach that model the decisions. GPT teaches. BERT acts.

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