与「Agent」相关的搜索结果

两个月之前我觉得 agent workspace（某种可拓展的分布式计算空间）是主要的问题，所以大家都在做类似的产品，wanman 也是其中之一，现在我越来越觉得动机发生器，也就是 intentware 才是重中之重。从哪里来，往哪里去，会成为拷问无数 agents 的首要问题。

Build a plugin once and use it across compatible agent clients. Introducing Agent Plugins, an open standard developed with @awsdevelopers, @cursor_ai, @github, @code, and @vercel that packages Agent Skills and supports MCP server configurations in a shared format.

herdr 真棒，自从之前推友介绍 agent skills 以后， 可以在 harness 之间可以互相召唤 互相指挥以后，很多场景都顺了。 如图是我用我的 review-forge 流程 做 code-review， 可以让 codex 先 review，然后它自动创建两个 agent panel，kimi k3 和 opencode 的 deepseek v4，去 review。然后主 codex 接收到两个 review 结果以后，生成 summary，我汇总 check 以后，再让 kimi 去修 bug，修好以后自动通知让 codex 去 verify， verify 后，kimi 再去读结果来回反复直到所有问题都解决，整个流程除了中间必须让我去 check 哪个 bug 要修之外，其他全都是自动化的，非常非常好用！

Ask Maps is getting an upgrade. 🔍✨ Now powered by agentic capabilities, real-time information, and Personal Intelligence, Ask Maps is transforming how you plan and move through the world.

啊这。人民网发文表示，呼吁媒体、教材和高校，多用词元、智能体等中文术语，少用 Token、Agent、LLM 等英文符号，其原因是它们仅作为 AI 领域单纯符号存在，不具备汉语形音义统一的特质。

X Layer has crossed 10,000 registered ERC-8004 agents onchain! As of Aug. 5, 10,126 of 10,463 registrations were attributable to the @OKX Agentic Marketplace. That concentration points to strong early traction for OKX Agentic Marketplace on @XLayerOfficial.

TapNow 正在招聘一名 Agent 工程师（QA 方向）。 你要负责把 QA Agent 调教好：让测试用例先行，让 Agent 能够可靠执行、正确判断、提供证据，并与开发 Agent 形成 TDD 闭环。 我们不要求传统测试背景，更看重你使用、开发和评测 Agent 的深度。如果你真正用 Coding Agent 做生产，并且想参与一个还没有标准答案的方向，欢迎来聊。 深圳｜builders@tapnow.ai

北京时间今晚7点（硅谷明早4点），CSDN 创始人蒋涛亲自下场聊Agent 近百个 Vibe Coding 作品之后，真正能上线的 Agent，难点已经不是 Demo 能不能跑，而是能不能接入真实数据、跑完长任务、失败后继续工作。 与 InfiniSynapse、InsCode 一起拆解：如何把 Agent 从“看起来能用”，做成真正可交付的应用

We tried using Meta's new Muse Code agent, but it has a bug that doesn't let it sign in from a docker container. So we did a fun experiment: Meta claims Muse Spark 1.2 was co-trained with their Muse agent harness. So we extracted instructions from their system prompt and added them to the Cline harness. TL;DR of this special prompting: - Trust source code over the user prompt, so read every call site and existing tests before starting the task - Weigh edge and error cases as heavily as the happy path - Always reproduce the bug before fixing - Don't trust the first passing test suite, and verify suspicious looking half-baked tests - Never stop at just editing, keep working until the change is verified complete. We then asked this modified harness to fix a real bug from our repo, and compared the results to the original Cline agent harness. Results: - Used 2.7x fewer tokens (19.7M → 7.2M) - Finished 2x faster (49min → 24min) - Cost 2.4x less ($7.69 → $3.25) Same Muse Spark 1.2 model, same task, only the prompting changed. Incredible how much of a performance gain Meta was able to achieve training it on these special instructions!