JevRiset

MotherDuck
@motherduckMotherDuck: Klasifikasi teks di MotherDuck kini ~50x lebih cepat dengan biaya ~1%. prompt_jev(
Localized reading
Klasifikasi teks di MotherDuck kini ~50x lebih cepat dengan biaya ~1%. prompt_jev() adalah fungsi SQL yang didukung Jev, model system one baru dari TypeSafe. 100 ribu baris: 40 detik, $0.50, akurasi setara LLM terdepan. LLM membutuhkan 32 menit dan biaya $37. Baca selengkapnya:
Original post / EN
Text classification in MotherDuck just got ~50x faster at ~1% of the cost. prompt_jev() is a SQL function powered by Jev, TypeSafe's new system one model. 100k rows: 40s, $0.50, frontier-LLM accuracy. The LLM took 32 min and $37. Read on:
- views
- 0
- likes
- 0
- saves
- 0
- reposts
- 0
Links and projects
This independent archive preserves a public post with attribution. Text, media, account details and trademarks belong to their respective owners.
