Skip to content
Zenteck
Latest
Why AI Safety Auditors Are Flooding Reviewers With False AlarmsCan a $32M Open Model Beat Big Tech? Inside Ripple-65BMeta Quietly Fixed AI Chat Clutter: What Are Muse Spaces?Can Mira Murati’s New Open Model Beat China? Here’s the CatchWhen AI Clears 80% of Fraud Queues, Where Do the Analysts Go?WhatsApp Just Added AI Outpainting: How to Expand Photos InstantlyHow Anthropic Used AI to Double Its Own Development SpeedPerplexity's $200 AI Agents: Are They Worth the Premium?
AI Tools

Jev: the new non-LLM AI model speeding up automation

ByAlex Silva1 min read0 comments
Jev-the-new-AI-model-without-language-for-automation
Photo: ZenteckCreated by a former OpenAI researcher, Jev drops human language to deliver text-free probability decisions that run up to 18 times faster.
Listen to article0:00 / 0:30

Segundo o TechCrunch, o ex-pesquisador da OpenAI Diogo Almeida lançou o Jev, um modelo da TypeSafe que abandona a geração de texto em favor de decisões probabilísticas.

Why did the creators skip human language?

Large language models optimize for human speech, which makes them inefficient for software automation. Jev outputs calibrated decisions rather than words. Because developers predefine the exact output structure, the model cannot hallucinate text.

How much faster is Jev in practice?

Engineering teams report massive efficiency jumps. Vercel replaced OpenAI's Luna model with Jev for safety classification tasks and achieved results 5 to 18 times faster. Meanwhile, Bryo AI tested Jev against Gemini for email sorting, finding Gemini 10 to 20 times more expensive.

Input tokens on Jev are metered by the billion rather than the million, while output tokens are entirely free. This pricing structure allows developers to use Jev for real-time model routing and monitoring other AI agents without inflating operational budgets.

Sources

  1. A new kind of AI model from a ChatGPT inventor is thrilling developers — techcrunch.com

Frequently asked questions

What is Jev?
Jev is a transformer-based model developed by TypeSafe that outputs probabilities and calibrated decisions instead of generating human text.
Why does Jev not hallucinate?
Because the model does not output open-ended text and users predefine the allowable outputs, text hallucination is entirely eliminated.
How does Jev's pricing work?
According to TechCrunch, output tokens are completely free, and input tokens are measured by the billion rather than the million.

Comments

0 comments

Deixe seu comentário

Your email is required for verification, but will never be published.

Be the first to comment.

RECOMMENDED

Continue Reading