What people are shipping with Jev.

16 hours ago ... Jev by TypeSafe returns typed decisions with confidence, not text, at up to 200x LLM speed. Why a non-hallucinating decision model fits AI agents.

14 hours ago ... What is Jev? Learn how TypeSafe AI's System One model makes fast, structured decisions, where it fits in the agent loop, and how to use Jev with LangChain.

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

It's super fun to play with @typesafeai 's #Jev with the #SREGym team. It's crazily fast and unlocks a lot of new capabilities for SRE use cases. A simple integration already leads

There's so much clutter on so much websites. 2-3 distraction can be enough overload the working memory and then you forget why you went to the site to begin with. This free exten

2 days ago ... TypeSafe's Jev is a new class of AI model, a System One Model, that returns typed decisions with calibrated probabilities instead of text, running 40-200x ...

16 hours ago ... Typesafe pitches Jev as a “system one model,” a different architecture built ... A Minecraft bot built by a developer using Jev reportedly ran for two ...

Found the perfect use case for @typesafeai Jev: instant compaction in 2026. Why is compaction still a summarization prompt? Jev scores every tool call and drops what’s irrelevant—m

@sawyerhood @typesafeai Taking a stab at it now. IMO auto is great, but given how fast this is, I think continuously giving feedback will give more confidence to the user. I'm go

@mandel59 match はパターンマッチで、noul, choice, score は jev 側のモデル抽象です。 一応アップロードしてますが、真面目に作ってないです https://t.co/MnfGTu5Zpi

@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

@thisiskp_ A PG CHECK constraint in plain english managed by Jev ;) https://t.co/UJ1eRWtaGm https://t.co/OoN1i1NPX6

So whats next? Got many ideas, but first we have to make this version stable and fully working. Currently 1m candles is the max I can get but i kind of want to scan on the 1s,5s

Using Jev to codify "flavor based" linters so code contributions reflect the style of the invoker

https://github.com/shauryajain07/ghost-user

@typesafeai One huge limitation is that I didn't add an actual LLM-monitor control. The goal was to evaluate and benchmark the capabilities of Jev. Full-write is at LessWrong: ht

Played around with @typesafeai Jev today, mostly to understand what it does for tool calling. Instead of an LLM deciding what to do, I substituted that part with Jev. My learni

TypeSafe raised $40M for Jev: typed decisions in one forward pass, calibrated. Closed weights, waitlist. I'm building the open version on one RTX 3090: Qwen3.8-27B, Apache-2.0, ev

@typesafeai https://t.co/dOsKPoWzJ3 Point it at an MCP server and it automatically probes the tool signatures, then runs a series of typed Jev calls to pick the right function and

Ok let's go 😃 Using Jev to find reviews of our apps from the last year to create a review database I will share the results when it finishes https://t.co/PPWhOBA98O https://t.co/h