Post-Cutoff

jev(): a PostgreSQL extension for natural-language search with no index or embeddings

Zachi @iam_zachiX

Why it matters

High-reach Jev developer demo (482K views).

Summary

Demo of a PostgreSQL extension that uses Jev to search a whole database in natural language, ‘No index, no embeddings, just one function’.

Metrics read 2026-09-30 via api.fxtwitter.com: 482,341 views.

Archived text

I think I just cooked something 🔥

jev(): a PostgreSQL extension that searches your whole database in natural language. No index, no embeddings, just one function.

WHERE jev(people, ‘could work from home’) or WHERE jev(people, ‘name sounds european’)

129 rows judged in ~1s for $0.0009. Second run: 6ms from cache.

Quoting @CompleteSkeptic: After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI?

I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev

• 20-200x faster • 40-400x cheaper (w/ output tokens free) • Frontier composable intelligence optimized for decisions

AFAICT the shortest path to AI-based economic revolution

Source: x.com/iam_zachi/status/2100679300756435135Archived 2026-09-29 via fxtwitter (unofficial).Counts: 482,341 views, 2,840 likes, 186 reposts, 126 replies (at fetch time)Media: video poster

Cited in

  1. Model releases 77 days after the cutoff

    TypeSafe AI releases Jev, a ‘System One’ decision model that returns typed probabilities instead of text