与「AgenticWorkflow」相关的搜索结果

Grok Build is crazy. 先不管GPT-5.6是不是release到底好不好用。 先來大大稱讚一下 @grok 的 Grok Build，目前唯一集大成的 coding agentic workflow。 Grok Build 內建 Image 生圖，甚至還有圖片生影片的功能，生圖速度真的快到不行，圖片品質也完全不比 Codex 差。 更厲害的是，因為 Grok Build 本身就內建生圖和生影片能力，agent 可以直接完成圖像與影片生成，不需要再額外串其他 MCP 或外部服務，只要訂閱 Grok，就可以把這整套 creative coding workflow 跑起來。 我在 Agent Sprite Forge 上面也新增了Grok專用的 video2dsprite，因為 Grok Build 內建影片生成，現在可以先生成一段連續的 6 秒角色動作影片，再反編譯成 game sprite，這樣做出來的角色元素圖會非常順，而且大幅減少之前常見的對齊問題。 Grok Build搭配 Agent Sprite Forge 真的超好用，我做完這個2D橫向卷軸遊戲總共花了不到30分鐘... 之前叫Codex做，光生圖就要花不少時間，要做成這樣的遊戲大概需要1~2小時，重點是Grok的品質還比Codex做的還要更好... @elonmusk Grok Build is crazy. Grok Build + Agent Sprite Forge feels like the future of agentic game development.

Tencent HY 3.0 在 OpenRouter 提供限时免费使用，这让开发者能以零成本为 Agent 配置一个具备 Frontier 级别的“大脑”。 对于需要高稳定性 Tool Calls 和长上下文处理的 Agentic Workflow 场景，HY 3.0 是目前性价比最高的选择。它支持 256K 上下文长度，且在 SWE-Bench 测试中拿到了 78.0 的成绩，足以应对复杂的工程任务。 接入方式极其简单，只需在配置中添加一行： openrouter/tencent/hy3:free 活动截止到 7 月 21 日，建议趁现在把原本昂贵的 Agent 推理成本降下来。

2026 年还在手动调优 Prompt 的人，本质上是在用 Google 时代的思维玩 AI。 大多数人的用法是“打字 $\rightarrow$ 看结果 $\rightarrow$ 再打字”，把 AI 当成一把随用随放的扳手，自己却成了驱动任务的引擎。这种低效的交互模式正在失去竞争力。 真正的 10x 产出者已经完成了从“对话”到“自主运行”的转型： 1. 从 Prompt Engineering 转向 Agentic Workflow：不再纠结于如何写出完美的指令，而是构建能够自我迭代、拆解任务并执行闭环的自动化流。 2. 从工具思维转向系统思维：AI 不再是回答问题的对话框，而是具备自主决策能力的数字员工。 如果你还在试图通过优化 Prompt 来榨取效率，你可能永远无法触及 AI 带来的指数级红利。

刚刚 Doubao-Seed-2.1-pro 发布啦! 给大家分享一个自我迭代 Agent 的构建技巧啊, 也是我在今天字节 seed-2.1 模型发布 demo 中用到的技巧. 这个技巧的核心就是, 干一件复杂的事情, 用两个Agent比用一个Agent要好. 简单来讲打工Agent干完活之后, 还要增加一个评审Agent, 这个Agent要给打工Agent的产出评分, 然后说明评分理由, 哪里做得好, 哪里做的不好. 然后, 一定要输出结构化的评分结果(JSON就行), 这样, 打工Agent接到评分后, 进行修改, 修改完毕再次交给评审Agent, 评审Agent再次打分, 这时候就可以跟上次的打分进行对比. 只有得分大于上次的得分, 你的框架才合并这次的修改. 这就是 Agentic 自我迭代了. 基于 AI 反馈的强化学习的雏形基本就是这样的了, 以及吴恩达提出的 Agentic Workflow 核心原则之一就是 Reflection（反思），框架让模型像人类程序员提交 PR一样：打工 Agent 提交 PR，裁判 Agent 跑测试、打分。只有 Review 通过才能 Merge 到主分支。这就是真正的“工程化迭代”了. 甚至我框架内其实就是采用的Git模式, 多个Agent进行并行评估模拟多个分支, 只有打分高的才会合并到主分支. 最终得益于 Seed-2.1 本身的自我迭代和多模态能力也很强, 在它的驱动下, 成功实现了这个【只需要上传一个城市的相册, 就能建模一整个城市】的demo. 相信在现场的同学已经看到这个 demo 了哈哈. 下一期告诉你当这个办法也失效了, 该怎么办☆. #AIAgent# #seed21# #AI自我迭代#

One of the new, buzzy jobs in Silicon Valley is the AI Forward Deployed Engineer (FDE), an engineer who is embedded within a client organization to help customize solutions, such as building and tuning agentic workflows that suit the client’s particular needs. I’ve heard from people who are wondering anew about the FDE career path since OpenAI and Anthropic started building new teams to place FDEs within client organizations. The rise of FDEs for AI workloads is one way AI is creating new jobs (and why the jobpolcalypse narrative of upcoming job market collapse is false -- there will be many AI and non-AI jobs). However, I believe there will be far more AI Engineer jobs than FDEs, as I explain below. The FDE role was pioneered about two decades ago by Palantir, which sent engineers to government locations to work on secure, air-gapped networks. In addition to having good technical skills, FDEs need communication skills and sometimes business skills. For example, they may need to speak with clients to understand their needs, formulate a strategy to prioritize projects, explain complex technology, and respectfully push back if a client asks for something unrealistic. They’re enjoying a resurgence because of the amount of work involved in taking an off-the-shelf LLM and building it into a custom agentic workflow that fits particular business needs. However, I believe the number of AI Engineer jobs will be far larger. A company might accept a few FDEs to be embedded within its organization. But most companies will want far more of their own employees working on their projects. While my organizations do hire FDEs, we hire far more AI Engineers! Also, a common client concern is that it is hard to find vendor-neutral FDEs — they are, after all, there to deeply integrate a particular vendor’s product into a company. In this moment when it’s hard to predict which AI service will be the best one in a year’s time, optionality (the ability to pick whatever vendor turns out to fit best in the future) is very valuable. In contrast, letting FDEs tightly bind a company’s processes significantly reduces optionality. Right now, I see surging demand for AI Engineers who can build software applications using AI software components (like LLM prompting, agentic frameworks, evals, etc.) and effectively use AI coding agents (like Claude Code, Codex, Antigravity CLI, and OpenCode). As the AI Engineer role matures, I expect it to fragment into more specialized roles, like the generic Software Engineer role from decades ago fragmented into frontend, backend, mobile, data engineering, devops, and so on. What will be the future, specialized AI engineering roles? I don’t know. Perhaps there will be AI FDEs, LLMOps Engineers, Evals Engineers, AI Data Engineers, Harness Engineers, and other roles we don’t have names for yet. But for now, I see a lot of AI engineers who are generalists create a lot of value. Skilled AI Engineers are in very high demand! As our field continues to mature over the coming decade, I look forward to new specializations within AI Engineering that create even more job opportunities. [Original text: The Batch newsletter]

Cerebras的IPO火爆，官方考虑大幅上调IPO定价区间。看路透社报道，Cerebras正考虑将IPO定价区间从此前的每股115至125美元上调至150至160美元，涨幅高达约28%。与此同时，公司还计划将发行股数从2800万股增至3000万股。若最终以每股160美元定价，Cerebras此次IPO募资规模将达约48亿美元。 个人看Cerwbras的核心优势在于：WSE-3推理领域已建立一定优势，tokens/second 可达GPU集群的15-20倍（低延迟场景下尤其突出）。Agentic workflow、reasoning models、长上下文推理正是其优势凸显的领域。 也拿到了大客户订单，OpenAI既是其股东也是签署了长期供货协议。而AWS已将CS-3集成到Bedrock，提供混合Trainium+ Cerebras推理方案。 相当于技术和产品已经得到了验证、商业化正在落地。 这个时机也很好，现在推理正在快速拓展、市场也希望能找到新的潜在英伟达挑战者、也会给更高的定价和预期。 个人看未来的空间看WSE-4如果能成功落地，成本/性能比将进一步拉大差距，让Cerebras从“高端替代”变成“主流基础设施”。 未来如果WSE-4成功=从“推理利基冠军”跃升为“AI基础设施第二梯队核心玩家”，市场空间进一步打开。 看到两篇关于Cerebras的推文，值得细看： @LinQingV 的这篇 @roger9949 的这篇