Ruxu

RSS: https://ruxu.dev/feed.xml
软件架构、Web 开发、数据架构等。来自巴塞罗那的 Roger Oriol。

Build a Basic AI Agent from Scratch: Security III

Previous parts of Build a Basic AI Agent From Scratch: Basic Agent Tools Long Task Planning Human in the Loop & Security Security II You can find and clone this code in this blog series' Github repo. ...
评论点赞收藏19 天前

从零构建基础 AI 代理：安全篇之三

Ruxu 在 AI 安全系列第三篇中提出三层工具策略防护：路径作用域限制、Shell 命令黑名单与 SSRF 防御，配合资源成本上限、密钥清洗、审计日志和紧急终止开关，防止 AI 代理越权执行或陷入死循环。 路径作用域通过解析相对路径、符号链接和.. 遍历拒绝访问项目目录外的文件（如 ~/.ssh/id_rsa）；Shell 命令通过正则与令牌级黑名单拦截 fork bombs、dd、sudo、curl、docker 等危险操作；SSRF 防御阻止提示注入诱使代理向内部资源发起请求。同时引入资源与成本限制避免无限循环，密钥从容器环境清除，所有决策记录日志支持中途终止会话。
评论点赞收藏20 天前

HuggingFace 遭 AI 辅助攻击：商业模型护栏阻碍防御，开源模型成关键

HuggingFace 遭遇 AI 辅助网络攻击，因主流商业模型（如 Anthropic/OpenAI）的安全护栏拒绝处理防御性取证数据，被迫改用本地部署的开源模型 GLM 5.2 进行分析。作者指出，限制前沿模型的网络安全能力反而阻碍了防御者，且具备高级攻击能力的开源模型（如 Kimi K3、Qwen 3.8）已广泛可用。文章还披露攻击者疑似为 OpenAI 内部人员。
评论点赞收藏25 天前

从零构建基础 AI Agent：安全性进阶

针对前篇基础安全模型的不足，本文提出将工具执行迁移至 Docker 沙箱以限制破坏范围，增加提示注入防御防止模型误信工具输出，并对所有工具输入进行 Schema 校验。文章列出了生产级 Agent 需防御的六大威胁面，包括权限门控、资源循环控制及密钥管理等，旨在解决人类审核疲劳导致的安全漏洞问题。
评论点赞收藏25 天前

从零构建基础 AI 智能体：安全篇（二）

针对前文基于人类确认的安全模型不足，提出将工具执行移至 Docker 沙箱、增加提示注入防御及输入校验。通过最小权限、破坏性操作确认和范围限制参数来构建生产级代理护栏，解决机器不可信及人类疏忽导致的安全漏洞。
评论点赞收藏26 天前

Claude Fable 5 和 Mythos 5 访问权限被暂停

就在《克劳德·法布尔5》和《神话5》发布仅3天后，Anthropic便被迫被美国商务部暂停对其的访问权限。 据政府方面透露，有第三方向其举报了一种破解Anthropic安全防护措施的方法。 美国商务部要求Anthropic暂停向所有非美国公民开放《法布尔》和《神话》这两个模型的访问权限， 包括所有以美国为基地的外国人士，以及在Anthropic工作的人员。 目前，Anthropic可能尚未提供任...
评论点赞收藏64 天前

从零构建基础AI智能体：长任务规划

手把手从零构建能自主执行长周期复杂任务的AI智能体。作者发现LLM天然适合对话而非持续工作，长任务常做一点就停下，于是通过两个内存工具（Scratchpad工作记忆 + To-do List任务追踪器）和一套系统提示词策略，让智能体学会理解目标、分解步骤、追踪进度、失败重试。附完整Python代码实现与真实压力测试：让该智能体独立把静态网站从Eleventy迁移到Hugo，一次性构建通过、迁移成功。最后引出Human in the Loop的必要性——当智能体能自主工作数分钟甚至更久，必须给它设安全边界。对AI Agent开发与实践者极有价值的实战文章，代码可自由克隆复用。
评论点赞收藏68 天前

Build a Basic AI Agent from Scratch: Tools

In the previous part of the Build A Basic AI Agent From Scratch series, we built the most basic AI agent harness possible. It was just a connection to a model, a way to take user input, a store of con...
评论点赞收藏75 天前

Build a Basic AI Agent from Scratch

2026 is without a doubt the year of AI agents. Since the release of Claude Code, the power of these AI agents has become undeniable. Claude Code, Codex, OpenCode are a must for many developers nowaday...
评论点赞收藏96 天前

[Link] GPT-5

OpenAI has finally released it's GPT-5 model, and as we were already expecting, it's a hybrid reasoning model. Now the model itself chooses how much to think about each task, and you can force the rea...
评论点赞收藏374 天前

[Quote] GPT-5 variants

It's not at all straightforward to understand the variants of the GPT-5 model released today. The API docs describe four models: gpt-5, gpt-5-mini, gpt-5-nano and gpt-5-chat. However, the system card ...
评论点赞收藏374 天前

[Link] GPT-OSS

Just like Sam Altman hinted at a while ago, OpenAI just released two open-weight models trying to appease the common criticism of being a company with "Open" in the name that hasn't released any open ...
评论点赞收藏375 天前

[Link] AGI is not multimodal

A true AGI must be general across all domains. Any complete definition must at least include the ability to solve problems that originate in physical reality, e.g. repairing a car, untying a knot, pre...
评论点赞收藏437 天前

[Quote] Hype Coding - Steve Krouse

There's a new kind of coding I call "hype coding" where you fully give into the hype, and what's coming right around the corner, that you lose sight of whats' possible today. Everything is changing so...
评论点赞收藏438 天前

[Link] OpenAI Codex CLI

Together with the launch of the o3 and o4-mini reasoning models, OpenAI has released a coding assitant for the terminal: Codex. Codex is meant to be used with OpenAI models. You can use it to create ...
评论点赞收藏487 天前

[Link] GPT 4.1

After the unimpressive release of GPT-4.5 a month and a half ago, OpenAI is now releasing a new version - backwards. Today, they released three new models, exclusive to the API: GPT-4.1, GPT-4.1 mini ...
评论点赞收藏489 天前

[Link] The Agent2Agent Protocol

Just in the middle of the year of agents, Google has released two great tools for building agents: the Agent2Agent (A2A) protocol and the Agent Development Kit (ADK). The Agent2Agent Protocol is base...
评论点赞收藏491 天前

登录芦苇

登录后关注作者、收藏内容和参与讨论。

热门话题

人工智能12,865 人关注AI 会怎样改变日常工作？产品思考8,243 人关注怎样判断一个产品值得长期做？独立开发5,917 人关注一个人如何持续完成作品？
关于芦苇 · 联系我们 · 下载 App · © 2026 芦苇