最近硅谷 AI 圈都在疯传的 Jev，彻底颠覆了我对 Agent 架构的认知。
This is a AI post classified by Jev as AI agents (a model release), kept by the AI Radar because it carries real work, not commentary.
最近硅谷 AI 圈都在疯传的 Jev，彻底颠覆了我对 Agent 架构的认知。 这是 OpenAI 前 ChatGPT / RLHF 核心发明者 Diogo Almeida 创立 TypeSafe AI 后放出的王炸： 它不写字、不生成文本、不聊天，而是一个纯粹的 “System-1 决策模型”。 为什么各大团队都在连夜改架构把决策权交给它？这份新鲜出炉的 10 页工程手册，把背后的逻辑讲透了 🧵👇
Posted by lifcc (9.4k followers) 1 h ago · 3 likes · 747 views · view the original post on X. Kept by the AI Radar as AI agents.
More AI work like this
- So far, I’ve used up 100 million tokens on Jev & still haven’t even finished the initial… — @DeryaTR_
- Just me and my Astra Agents tonight — @benitoz
- ChatGPT co-inventor just shipped a different kind of AI. — @minchoi
- The next chapter of AI is agentic. — @alibaba_cloud
- Me to @aadithyanr_: can you look into this muse connector thing — @mynameisyahia
- everyone is pruning agent context with @typesafeai Jev now — @AstroHanRay
- Pentest is not a workflow, It is a search problem. — @0x0SojalSec
- 706k params just filled a form better than a hosted computer-use API. — @0x0SojalSec
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 31.7k posts from 4.8k X accounts over the last 14 days, 1.3k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-20 04:05 UTC. Full method.