What people are shipping with Jev.

Jev provide us an awesome way to make PR reviews in less than 30 seconds! #jev #typesafe #review #flash https://t.co/Um7vHxFGLT

Been using Jev by @typesafeai and it feels like a glimpse of a different AI future. High-throughput, low-latency intelligence means AI can run inside every loop, reacting in real

@obie @Quentin_Adt @typesafeai That’s the thing people don’t understand, it’s a V1 model with so much potential. Using Jev alongside normal LLM as an co-partnership between two ty

@NavDoesTech @AsideAI @typesafeai not quite. nothing about the site needs to be known beforehand. the browser hands you the real candidate set at runtime. that's what @AsideAI is b

@frmdomi @AsideAI @typesafeai if u mean agentic = generative, yes, jev can't write prose. but agency isn't generation, it's the observe decide act verify loop, and that's literally

I spent a morning testing a model that can't write. Fun! -> Jev, from @typesafeai You hand it a document and a fixed form: pick one of these options, answer yes or no, place

@jpschroeder @typesafeai Maybe we find a way to record Jev model behaviour and potentially make it free to use by finding a way to replicate the decision behaviour.

@HacksonClark @typesafeai That boundary is key: Jev ranks next tests/evidence; it shouldn’t diagnose. Keep tests closed and inspect 2 regressions as calibration failures (was confi

@embw_l0x @typesafeai Yep, we already did. I think I have a very strong candidate for Jev. Our mind memory could be massively improved here.

This lad is a cracked dev. Follow him if you want to see real examples of what's possible with the latest AI automation to get your gears turning (like this demo using Jev). https:

2 days ago ... I was also thinking of testing it with some real-time video games, but I realised it doesn't take multimodal data, and their Doom demo was using an AI model ...

jev demo night at betaworks next week - let @kayacancode know if you want to demo 🪄 https://t.co/IgiAOzxShi cc @typesafeai https://t.co/oyshSUjO8q

@alexatallah @typesafeai low-entropy routing only pays if the classifier is cheaper than sending the PR review to the frontier model. are you actually splitting those three buckets

If you combine this with Jev by @typesafeai you could get 1000 scored leads for $0.20 Thank me later https://t.co/t6DIVcFKS9

Spent last night playing with @typesafeai's Jev. The exciting part: it doesn't return text. You ask questions, it returns numbers like 0.98 (a noul, a choice, a score) ready for co

Jev by @typesafeai turns your  Mac into an AI agent... what this means for You ? - Jev, a new model from a ChatGPT co-inventor, can operate computer tools in real time. - It is

@pdp @typesafeai Decision API as a first-class surface is the right packaging. Agents keep the generator; /v1/decision/create owns the gate. Curious — are you routing tool choice

@ForwardEditor What ways are you using Jev for?

OpenTelemetry Instrumentation for AI Observability

@DoveLocke7kj3 @harshilmathur @typesafeai Jev is TypeSafe’s System One model for fast structured decisions. You send it program state plus typed questions (choice from options, sco