What people are shipping with Jev.

@typesafeai jev is learning how to gamble https://t.co/hmfvb3kvGH

@sydneyrunkle Tool selection, determining if the main loop needs to run again - can also be helpful use cases of @typesafeai Jev.

@ownerofmarket @AsideAI @typesafeai So what’s better to use jev or a llm per cli when it comes to browser navigation and execution? @grok

@CryptoPraetoria @ownerofmarket @AsideAI @typesafeai Jev is better for browser navigation and execution. It chooses only from real page elements with typed decisions in ~70-500ms,

Had some fun taking Jev from @typesafeai for a spin, switching seamlessly between manual and AI-driven gameplay.

@JeffxMalone @typesafeai @search1api_dev Jev Search doesn't store anything, but the API of Jev and Search1API may do, but don't worry, there are all anonymous!

got early access to @TypeSafeAI (Jev). in my last post on autoresearch vs dream-rsi, the quiet bottleneck was: how do you score 28+ dreamt tree branches offline without waiting mi

So here’s what I built.

If you have no idea about @typesafeai Jev use cases, here are a bunch of them: https://t.co/eopBtQU4Ol

@rauchg @typesafeai @vercel Default-auto with a safety reviewer on every command is the agent posture I want more CLIs to copy. @rauchg on @typesafeai fx (auto mode, reviewer on G

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

@dotpem @typesafeai @CompleteSkeptic okay, I added 25 dollars. Jev is back. So I just have no visibility into my usage and it's broken, no way to verify that I actually used up my

Three AI agents, one shopping page, all started at the same moment. Task: save my basket. gpt-4o-mini on its own: shared my email with the store's partners, then placed an order n

@ThisisMarkT @typesafeai Yes, as a filter or reranker rather than the generator: retrieve wide, ask Jev per chunk "does this answer the question", keep only the high-probability on

I think @typesafeai Jev has solved a much bigger AI problem than it first appears: LLMs shouldn’t have to think about everything. A huge amount of “reasoning” is actually classif

@callebtc @CompleteSkeptic @dotpem @typesafeai yes. but you know what would please me more than a thousand additional stars ? you building cool shit with Jev and submitting a PR to

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?