Jev, AI Gateway 역사상 가장 빠르게 퍼졌다 — 첫날 팀의 13%, Fable 5.1의 6배
Vercel이 Jev가 AI Gateway 역사상 어떤 모델보다 빠르게 채택됐다고 밝혔다. 첫날 전체 팀의 약 13%가 썼고, 이는 GPT-5.6 계열의 2배, Claude Fable 5.1의 6배다. 나흘째 쓰임새가 계속 늘고 있다. Claude Code용 모델 라우터(요청마다 Jev가 서브에이전트 모델을 분류), 컴퓨터 조작 도구, 로봇 제어 실험(MuJoCo에서 GPT-6 Astra와 비교), 면접 기록 100명분을 12.8초에 통과/보류/탈락으로 분류하며 든 비용 0.005달러, SEO 작업 비용을 250달러에서 25달러로 줄였다는 사례까지 나왔다. TypeSafe는 테스트에서 최대 193배 빠르고 444배 싸다고 주장한다. 반대 방향 사례도 있다. Jev로 만든 자율 트레이딩 봇을 하룻밤 돌린 개발자는 "지금까지 31,680달러를 잃었다"고 적었다.
댓글 반응 3개
- @MoonGotchi♥4천
Jev is INSANE. I built this in an evening and morning. A real-time trading bot ingesting onchain+offchain data to make rapid decisions about trades. Fully autonomous. So far it has lost me $31,680. - @dehu_wang
This is false . I tested several Jev alternatives and none of them is even close to Jev in terms of quality and accuracy. - @Abhhinav_SB♥1
An oversimplified explanation of jev is RL over sequence embeddings. I have seen others doing the same before like using PPO over learned representations for downstream decision classification tasks, which is almost the same and works as non autoregressive.
출처 7건 보기· @vercel, @MoonGotchi, @dani_avila7 외 4
- @vercelJev was adopted faster than any other model in AI Gateway history. In the first day, @typesafeai reached ~13% of teams, 2x the GPT-5.6 family and 6x Fable 5.1.X ♥2.2천
- @MoonGotchiJev is INSANE. I built this in an evening and morning. A real-time trading bot ingesting onchain+offchain data to make rapid decisions about trades. Fully autonomous. So far it has lost me $31,680.X ♥4천
- @dani_avila7Introducing Jev Model Router for Claude Code This Claude Code Mod lets you use Jev through its direct @typesafeai API or @vercel AI Gateway With every request you send to Claude Code, Jev classifies the subagent model, main model (only at session start to avoid breaking the cache), and effort level Install it with one command: npx claude-code-templates@latest --mod productivity/jev-model-router Full Mod details:X ♥1.2천
- @masa_okamura108JEV、すごい。面接議事録100人分（架空データ）を渡したら ・12.8秒で全員を「通過／保留／見送り」に仕分け ・専門スキル、コミュニケーション、志望度をスコア化 ・「重大な懸念あり」の議事録も検出 コストは全部で$0.005。1人あたり0.01円以下。 文章生成ではなく評価・判断専用モデルなので、速くて安い。 採用文脈なら「どの部署に適性があるか」の判定、一次スクリーニングの補助、面接官ごとの評価のばらつきチェックなど、使い道が広そう。X ♥1.5천
- @HamonPaulmJev just killed 90% of my seo/geo costs. this is insane. one agent run that audits and fixes a client's seo/geo used to cost us ~$250. now it's ~$25. same output. not a better prompt. not a new workflow. not a cheaper freelancer. just 30x faster on the boring parts: → reading search console + posthog/mixpanel → checking what chatgpt actually searches on bing → modeling what users ask gemini and claude → scanning who chatgpt and claude cite → digging into the sources behind those citations →X ♥496
- @openrobotoJev by @typesafeai might change how we control robots. We compared Jev, GPT-6 Astra and GPT-4.1 mini in MuJoCo. One apple. One plate. Each model chooses intent → X/Y/Z direction + gripper open/hold/close. 🧵X ♥240
- @DataChazJev might genuinely be an “Internet moment” for AI. TypeSafe reports up to 193x faster and 444x cheaper performance in tests with Claude Fable 5.1 and GPT-6 Astra. @0xCodila just wrote a great 10-page article explaining what Jev is, how to use it, and where its 100x advantage comes from. Here are the 10 steps: 1 → LLMs create. Agents act. Jev decides the next move. 2 → Turn agent forks into three primitives: Choice, Score and probability. 3 → Build with OpenAI, Anthropic or xAI first, thenX ♥891