ChatbotsChina发起人 • 微博：@breezedeus • 博客：breezedeus.github.io 目录 • Chatbots简史 • 三个火枪手：三个Bot框架 • IR-Bot、Task-Bot、Chitchat-Bot • 爱因互动所做的事 • 总结 Chatbots简史 1950 • 提出 “图灵 测试” 1966 •ELIZA：MIT 发展的精神 治疗师 chatbot

Retention Google Search Retention +2,259 bps AI User + Usage + CapEx Growth = Unprecedented85 AI Chatbots @ Work Tells = >72% Doing Things Quicker / Better Note: N = 5,273 USA adults who are employed part primary job were surveyed. Source: Pew Research Center (10/24) % of Employed USA Adults Using AI Chatbots Who Say Tools Have Been ______ Helpful When It Comes to… – 10/24, per Pew % of Employed USA Adults Work Allowing Them to Do Things More Quickly Extremely / Very Somewhat Not Too / Not at All86 AI Chatbots @ School Tells (ChatGPT as Proxy) = Bias to Research / Problem Solving / Learning / Advice OpenAI

自动化、精准的文本处理 2. 智能化的且易于理解 3. 将语义加入文本当中 4. 定制化的发音 文章、博客 训练材料 Chatbots (Lex) 公告 第一代: 面向机器的交互 第二代: 面向控制& 翻译 第三代: 意图导向 人-机交互会话的发展 语音 & 文本 “Chatbots” Alexa 应用 在手机、Web以及 设备上的语音交互 在Slack & Messenger 上的文本交互

Applications that integrate LLMs but don’t use them to control workflow execution—think simple chatbots, single-turn LLMs, or sentiment classifiers—are not agents. More concretely, an agent possesses

to the size of WeChat groups and the non-public discussions, they need auxiliary tools such as chatbots to reach the communication needs of open source communities. 4.7 开源社区中重要的角色 / 4.7 Important searches, such as 3D models for game production companies, graphics for e-commerce sites, and Q&A chatbots that understand mixed semantics. Jina has also been recognized by several leading investors in

在投资机构和⼤⼚的内部综合评测中，Kimi智能助⼿的中⽂实⼒直追
OpenAI。
b. 根据“AI产品榜aicpb.com”的统计数据，2024年1⽉Kimi智能助⼿的访问量
142
万，在⼤模型 创业公司的“AI
ChatBots”产品中排在第⼀；⽉环⽐增⻓率
94.1%，增⻓速度也在⼤模型创业 公司的第⼀位。
“Kimi
智能助⼿”详细介绍
Kimi
是由⽉之暗⾯（Moonshot
AI）提供的超⻓记忆
A

S. Wei, and X. Zhu, “Speaker-aware BERT for multi-turn response selection in retrieval-based chatbots,” in CIKM ’20 [15] K. Filippova, E. Alfonseca, C. A. Colmenares, L. Kaiser, and O. Vinyals, “Sentence “Sequential matching network: A new architecture for multi-turn response selection in retrieval-based chatbots,” in ACL 2017, [30] Z.Zhang,J.Li,P.Zhu,H.Zhao,andG.Liu,“Modelingmulti-turn conversation with Li, D. Dong, Y. Liu, Y. Chen, W. X. Zhao, D. Yu, and H. Wu, “Multi- turn response selection for chatbots with deep attention matching network,” in ACL 2018 [32] C. Tao, W. Wu, C. Xu, W. Hu, D. Zhao