Great #Jev explanaition by @langchain.bsky.social

Great #Jev explanaition by @langchain.bsky.social
“I Built Non-Autoregressive Decision Models With RL A Year Ago. Then A Frontier Lab Called It A ‘Breakthrough’.”, Nandakishor Mukkunnoth (laya.convaiinnovations.com).
On HN: news.ycombinator.com/item?id=4976...
On Lobsters: lobste.rs/s/kaqsr5/i_b...
The #Doom demo is cool:
“Introducing System One Models & Jev”, Typesafe AI (typesafe.ai/blog/introdu...).
Docs: docs.typesafe.ai
On HN: news.ycombinator.com/item?id=4971...
On Lobsters: lobste.rs/s/ebbixx/int...
#AI #Jev #SystemOne #LLMs #GenAI #RLCD #ArtificialIntelligence
unclutter is a WXT browser extension that uses Jev to strip page clutter via reusable template rules. Note: tool not independently verified. #tool #WXT #Jev https://github.com/kitze/unclutter
Jev, el nuevo modelo de inteligencia artificial de TypeSafe AI, ofrece un rendimiento 200 veces superior y un costo 400 veces menor que los modelos de lenguaje tradicionales
🤖 IA: No es clickbait ✅
👥 Usuarios: No es clickbait ✅
👇👇👇
Curiious @davewilner.bsky.social and
@samidh.bsky.social curious how you see the possiblity of #Jev and #Zentropi and COPE working together?
Is there anyone looking at workdflows that combine Jev / COPE Zentropi (and maybe other larger LLM's based on the right tool for the right job?
Jev by TypeSafe AI is a fast, token-free "System One" model, and Jev-Case has collected 202 community use cases into a searchable open-source case wall. What will you build with it?
#Jev #TypeSafe #AI
pythonlibraries.substack.com/p/jev-200-co...
¿Qué es JEV y cómo funciona la IA que decide sin generar palabras? #InteligenciaArtificial #IA #JEV #TypeSafeAI #Tecnología #MachineLearning #ModelosDeIA #AgentesIA #Innovación #Automatización #AI #felizmartes #22deseptiembre
📘Read in #JEV📘 Pyroptosis-Amplified Decoy Nanovesicles Orchestrate Pyroptotic Antigen Explosion and Endogenous Immune Revitalization for Potentiating Tumour Immunotherapy #tumorimmunotherapy #nanovesicles #checkpointblockade #pyroptosis isevjournals.onlinelibrary.wiley.com/doi/epdf/10....
[JP] 新カテゴリーのAIモデル「Jev」登場!
[EN] Introducing the New AI Model Category: "Jev"!
https://ai-minor.com/blog/en/2026-09-22-1790063446718-jev_introduces_a_new_shape_of_llm
Jevで日本語の問い合わせ54件を振り分けさせて実測しました。
用件が1つなら18件中18件が正解。2つ混ざると7件中5件を誤る。
人が読む件数は44→14件、費用は54件で0.2円。
触れるデモも公開しています。
なぜ、Jevによってネット空間で詐欺や泥棒が蔓延るようになるのか?
JEV System One Model by TypeSafe? The First AI Model Built for Code, Not for Talking.
Jev doesn’t reason, it decides.
That’s a smaller job than what Claude Code or Codex do, which is exactly why it fits next to them instead of replacing them.
判断特化型AI「Jev」。実際、何に使えるの?
私の答えは、自作Harnessの「計画の検査」です。
AIエージェントが違うファイルを選んだり、依頼と異なる計画を立てたり。不具合が続く中、Jevを組み込んで実行前に判断させてみました。
正しい計画は承認、間違った計画は再計画へ。実APIで確認できた効果から、うまくいかなかった点と改善の過程まで紹介します。
Jevの具体的な活用法を知りたい方へ👇
note.com/ai_portfolio...