What people are shipping with Jev.

Hey @typesafeai, the usage statistics hasn’t been updated for about 2 days, Can you have a look? #jev

@fazxes @typesafeai vercel fx safety mode on jev is interesting. false allow rate at the prod threshold beats another relative speedup chart

Has anyone used Jev by @typesafeai . It's incredibly cheap, but I can't think of any practical use cases for it right now.

@typesafeai built an AI that can’t write you a single sentence but is also one of the most intelligent, cheapest, and fastest models ever. In Thinking, Fast and Slow, @kahneman_da

Inspired by @typesafeai's Jev, I built sarvam-jev - an open engine that reads typed decisions straight out of an Indic model's logits instead of generating JSON token by token. S

Jev from @typesafeai is now available as an evaluation model in Braintrust. If you have an existing scorer, just change the model in the dropdown to Jev and reduce your scoring co

If you've heard about Jev from @typesafeai but still don't really have any idea what it can actually do, here are some examples. Jev doesn't write code or content, and it doesn't

@JoshARosen @typesafeai jev watching coding agents for progress/tests/drift is free senior qa energy. intervention precision matters - unnecessary intervene % vs missed drift

Jeżeli chcecie coś budować z nowym modelem od @typesafeai , to tutaj polecam wam dwa skille 1. typesafe-ai od @typesafeai Oficjalny i znacznie szerszy skill, który jest takim pr

@braintrust @typesafeai productizing jev as a trace scorer is the natural seat. high-conf disagreement with human soft-fail is the miss card - shadow dual-scorer on last n evals

would love to hear how application like Clay (& @jeffbarg) think about the new @typesafeai / jev model and the family of models as a whole. seems like a great fit for highly p

estou com fomo pessoal, libera o acesso ao jev @typesafeai, preciso testar a tecnologia de vcs esse final de semana

@o_kwasniewski @typesafeai nice. the failure mode id watch for on agent-e2e is treating the clicker and the oracle as one model. keep actuation (playwright/agent) separate from ju

Three weeks from now on LinkedIn: Check out this Jev model from @typesafeai that JUST CAME OUT and an image of a tweet with all identifying marks studiously cropped

@o_kwasniewski @typesafeai jev in the e2e loop is where flake shows. same scenario ×10 high conf flakes from dom timing vs boolean ready gates

@typesafeai Jev is like shopping with a guy. LLMs are like shopping with your girl. Guy: that’s it, 90%, we’re out. Girl: try it on, check the other store, does it match your oth

@jpschroeder @typesafeai Good post, totally agree. We're at the very beginning of the volume adoption curve, and I would expect pricing to drop dramatically as they beef up their

Let me in to Jev I need this for the weekend pretty plssss @typesafeai @notkevinzhang

Everyone got access to JEV @typesafeai when are you inviting the next wave?

There's been a lot of chatter about Jev from @typesafeai this week, and we immediately got curious about what it means for how we build agents. So we got to work and dug in. Here'