News, how-tos and research on the Jev model. Every article lists its sources and check date.
The Jev-LiteMAS preprint let Jev route agents and screen intermediate results. Generative-model tokens fell by 12.7 to 54.6%, while accuracy stayed close.
Read articleA preprint compared Jev 1.13 with GPT-6 Astra on RAG claim verification. Accuracy was similar and Jev far cheaper, but it passed unsupported claims more often.
Read articleA preprint from 12 October 2026 reports that jev-1.13.0 probabilities depend on which other options a Choice question lists. What it means for online shops.
Read articleOn 14 October 2026 TypeSafe released jev-1.14.0 as a preview with Box, a question type for finding things in images. What changed, the limits, and why not production yet.
Read articleA preprint from 13 October 2026 found that injected text flipped Jev's decisions in 81.5% of cases across 228 apps. Common defences helped only a little.
Read articleA preprint from 6 October 2026 tried Jev as a check on whether AI calculations cite the right figure. It added one record over a rule and shifted with table format.
Read articleA preprint from 9 October 2026 put Jev into five types of AI agents. Single decisions got cheaper, yet task success dropped in places. What it means for developers.
Read articleA new preprint compared Jev with 19 language models on 13 tests. It keeps pace on knowledge tasks and trails on maths. What this means for a Slovak online shop.
Read articleA USC preprint reports that typed decision models follow option labels more than written definitions. What this means for Choice questions in an online shop.
Read articleSince 6 October 2026, Vercel AI Gateway can rerun a Jev decision with another model when confidence is low. Conditions, costs and traps explained.
Read articleA University of Cyprus preprint compared Jev 1.13 with GPT-6 at classifying hateful posts. Accuracy, cost, latency and what it means for online shops.
Read articleClaude can write and plan; Jev can answer narrow decision questions. A practical Claude Code setup, safe API key handling, and limits for automatic permissions.
Read articleYou do not need to install Jev or join a waitlist. Use OpenRouter to create a limited API key and run your first yes-or-no decision in Windows PowerShell.
Read articleA new preprint compared Jev 1.13 with 16 AI judges. It was enough for confident verdicts; uncertain ones went to a stronger model. The study’s numbers, weaknesses and limits.
Read articleNew articles are also available via the RSS feed.