What people are shipping with Jev.

you could build the next billion dollar startup with just @ExaAILabs and jev by @typesafeai

@building_KR BOZO SCORE 100 / 100 종결 BOZO · 파산 예정자 팔이 ██████████ 99 정신승리 ██████████ 100 자아 ██████████ 99 공허 ██████████ 100 형식 ██████████ 100 "마틴게일을 리밸런싱이라고 부르는 파산

My entire feed is just Jev rn. The level of excitement is so palpable. Very excited to see all the products that will be improved by it. Congrats to @typesafeai team!

Played a few rounds of https://t.co/Gw1MRUkQRF today and I gotta say, this is actually really fun 😁 Probably the first game built with @typesafeai Jev?

@TheBalkanHacker @typesafeai @dotpem Sick, how did you get into jev?

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

@mormonnegro @typesafeai que crack! construi un catalogo con recursos de Jev y subi tu caso de uso ;)

Interesting idea from @TypeSafeAI: Jev, a “System One Model” built for decisions, not text. Instead of generating JSON and parsing it, Jev returns typed decisions + probabilities.

Jev from @typesafeai can replace your LLM-as-a-judge for scoring agent responses. It returns a choice or numeric result with information about uncertainty, so you don't need to sp

If JEV is going to end the era of hypersensationalism of AI, and the overextending Papyrus Responsens, welcome @typesafeai , we love u. https://t.co/wAW130PnCW

@tamarajtran @typesafeai @tamarajtran added your Jev build to https://t.co/z0izy4XNao

@typesafeai Seems Jev didn't agree with this math too 🤣 https://t.co/M580e4Xlvs

@kyamilass @typesafeai Jev showing up on these lists this fast is wild 👀

Time taken seems to be increasing over time, @typesafeai ' JEV seem to be getting busier 👀 Try https://t.co/V7CgA6iISc https://t.co/IbZapgMPVx

JEV is sooooo different and fast @typesafeai

@o_kwasniewski @typesafeai is Jev classifying pass/fail after the run, or driving the clicks? a classifier I can slot in. a Jev-driven UI loop is a different harness.

@typesafeai Jev is moving fast - browser use, context compaction, RAG, agent harnesses, even a programming language. I went down the rabbit hole on how it works and why these use

@typesafeai @parsewise 2. Jev was a lot more literal when following instructions, meaning I had to tune the task guidance more so than LLMs. E.g. explaining that small indirect c

tldr of Jev by @typesafeai https://t.co/tZsPwnWPBS

Board: https://t.co/bQMPwlAInH Climber: @GravitateCRE Built by: @mattyp @poteto @roshan_s / @thursdayarena Jev: @typesafeai @CompleteSkeptic Also: @grok @xai