内置说服意图披露功能的AI聊天机器人，主动告知劝说目的，有效提升对话透明度，减少诱导操控感。
arXiv:2608.11794v1 Announce Type: cross Abstract: The growing role of AI-generated content and AI-enabled systems in public communication has led regu…
让 LangChain 智能体互相发现并建立信任，还汇总了多款搜索工具的免费额度，上手零成本。
Article URL: https://docs.langchain.com/oss/python/integrations/tools Comments URL: https://news.ycombinator.com/item?id=49227511 Points: 2 # Comments…
记录Agent执行轨迹以建立信任和复用，让大模型任务更可靠、可复现。
arXiv:2607.18816v1 Announce Type: cross Abstract: LLM-powered agents increasingly tackle complex tasks by invoking tools, querying databases, executin…
去中心化学习如何兼顾个性与信任？这篇论文给出了无信任框架的新思路。
arXiv:2410.11378v3 Announce Type: replace-cross Abstract: Personalized collaborative learning in federated settings faces a critical trade-off between…
AI生成内容正在改写创作与信任的规则，一场关于责任与伦理的社会契约讨论。
Article URL: https://www.jeromehollon.com/projects/ai-writing-social-contract/ Comments URL: https://news.ycombinator.com/item?id=48818153 Points: 1 #…
论文揭示不可靠反馈如何破坏LLM代理的工具使用能力，提醒不要盲目信任反馈机制。
arXiv:2606.21409v1 Announce Type: new Abstract: Tool-augmented agents are typically evaluated by their gains under reliable external feedback. Yet the…
探索商业场景中人类与AI代理的交互模式，实证揭示协作效率与信任建立的底层逻辑。
arXiv:2606.18716v1 Announce Type: cross Abstract: As AI agents are increasingly integrated into core business processes, understanding and designing e…
macOS/Linux 上的开源包管理器，6.0 版引入 Tap 信任机制，更安全地管理第三方软件源
IT之家 6 月 12 日消息，当地时间 6 月 11 日，适用于 macOS 和 Linux 的开源包管理器 Homebrew 发布了 6.0.0 大版本更新。 Homebrew 是一个免费且开源的工具，能通过终端（Terminal）输入简单的指令，来快速安装、卸载、更新和管理电脑上的各种软件及开…
新协议ACUTE通过激活操作提升语言模型的校准度、实用性和可信度，为AI安全提供新思路。
arXiv:2606.07822v1 Announce Type: cross Abstract: As language models improve and become increasingly deployed to solve a variety of tasks, trustworthi…
Vanta公开其构建AI产品的核心原则：拒绝无用的“AI撒盐”，专注真正解决客户问题的信任机制。
Article URL: https://www.vanta.com/resources/how-we-build-ai-products-at-vanta Comments URL: https://news.ycombinator.com/item?id=48394581 Points: 1 #…