Workflow
通用Agent
icon
Search documents
摸着 Manus,字节百度开始过AI Agent这条河
3 6 Ke· 2025-04-27 09:42
通用 Agent(智能体)的火爆,仍在继续。 两者都在尝试打破各自内部的生态壁垒,构建更广泛的AI Agent生态体系,将通用Agent概念彻底打入用户的心智。 然而,受限于大模型技术的成熟度,包括字节、百度在内的所有参与者,都不得不在探索的路上,不断地扪心自问:AI Agent的真正应用场景是 什么? 01 引爆这一领域的明星初创公司Manus AI,近期被曝出完成了新一轮7500万美元融资,估值在短短不到2个月内,飙升至5亿美元。 追逐AI Agent的场景答案 被Manus打开未来想象空间的通用 Agent市场,正在吸引一众科技大厂的入局。最新加入进来的是百度。 在找寻差异化应用场景的道路上,字节与百度在这一问题上选择了不同的路径。 近日,百度对外推出了类通用 Agent产品"心响"。百度之前,字节抢跑一众国内科技大厂,率先上线了自家的Agent产品"扣子空间"。 相比传统Agent产品,通用Agent本质区别在于其定位从"工具"向"伙伴"的角色转变,能够处理复杂、多步骤的任务场景。 背靠大厂已有的产品生态,字节和百度共同盯上了同一目标,即借 AI Agent寻找自家 AI 产品体系的新增长点:字节试图 ...
扣子空间—字节的agent
小熊跑的快· 2025-04-20 23:52
4月18日晚间,字节跳动扣子空间开启内测,定位通用Agent。与其他类似产品如manus一样,扣子空间采用了邀请码制。平台上,用户可以选择精通各项 技能的通用实习生,也可以选择行业的领域专家,通过与 AI 的互动完成工作任务。 据官方介绍,扣子空间主要有以下特点: 2) 拥有 专家Agent生态 :华泰A股观察助手可以为用户进行每日早报生成、针对股票分析问题、答疑解惑;用户研究专家可以协助进行用研资料深度分 析,获取更多用户洞察。 3) 探索/规划双模式 ,人机协同完成高难度任务:用户如果想一步到位输出,可以选择探索模式、如果想亲自把控每个步骤,可以选择规划模式。 提问: 现在要写一篇关于扣子空间的内容 , 请帮我规划一下,告诉我该从哪些方面入手。 扣子空间 第一步 会将 需求提炼出来,整理成提示词 , 并说:第一步要先收集信息,第二步要规划文章逻辑,第三步梳理逻辑,最后一步结构化输出, 这些提示词我可以改,也可以直接点开始。 执行步骤 比较清晰 ,按照上面的提示词 逐步执行 ;不过整个过程时间比较长,因为规划步骤多 ,执行时间约10分钟 。 执行过程中,用户能 清楚看到 每一步的 思考 过程,搜索范围和深度 ...
一手体验:首款通用Agent产品Manus,效果如何?
虎嗅APP· 2025-03-06 10:23
Core Viewpoint - The article discusses the launch of Manus, the first general-purpose AI agent product, which is perceived as a significant advancement in AI capabilities, surpassing existing models like OpenAI's DeepResearch and Claude's Computer Use [2][5][8]. Group 1: Manus Overview - Manus is described as a groundbreaking project that combines the best features of existing AI models and can perform complex tasks such as coding and task planning [5][6]. - It has achieved a high score in the GAIA (General AI Assistants) benchmark, surpassing OpenAI's DeepResearch [8][10]. Group 2: GAIA Benchmark - GAIA is a benchmark testing system for general AI assistants, introduced in 2023 by Meta AI and Hugging Face, consisting of 466 carefully designed questions [10][11]. - The benchmark assesses various capabilities, including web search, tool usage, programming, and document processing, with a success rate of 90% for humans and only 15% for GPT-4 at the first level [14][13]. Group 3: Manus Capabilities - Manus can decompose complex tasks into manageable steps and execute them autonomously in the cloud, providing users with real-time updates on progress [22][24][36]. - An example task involved converting a PDF paper into a PowerPoint presentation, where Manus successfully extracted information, summarized it, and formatted it according to specific requirements [25][40]. Group 4: User Experience - The user interface of Manus is designed for intuitive interaction, allowing users to see the progress of tasks in real-time, enhancing the overall experience [37][38]. - Users have reported high satisfaction with the output quality, noting that Manus can produce well-structured and visually appealing documents [41][60]. Group 5: Competitive Landscape - Manus is positioned as a strong competitor in the AI space, with its capabilities leading to comparisons with existing models like OpenAI's DeepResearch, which, while high quality, lacks the same level of readability and interactivity [56][57]. - The article emphasizes the rapid advancements in AI technology, suggesting that Manus represents a new height in agent engineering [69][70].