AI 教程与实战

如何在你的小企业中用好 OpenClaw @hrudolph 和 @Pat_Erichsen 与 @ArkStabler、@heyneighbor 聊了方案、线索和可复用技能。@Pishgar 稍后加入，介绍社区论坛。 The ClawCast 第 13 期： https://openclaw.ai/podcast/episode-13

In Part 1, I wrote about the uncomfortable part of AI-assisted engineering: the tools are becoming...

vLLM 团队介绍如何通过异步准备与 NIXL EP 让 Elastic Expert Parallelism 在扩缩容时实现近零停机。在 DeepSeek V4 Pro 的 GB200 基准中，16 到 20 GPU 扩容停机从 99.62 秒降至 0.82 秒，缩回时降至 1.96 秒。

Google Developers Blog 发布智能体评测实践指南，指出仅靠终端跑几个提示词的 vibe check 无法发现智能体重试循环、工具参数幻觉等隐性失败。

FactSet 借助 Databricks AI Runtime 的无服务器 GPU 基础设施，将其 Text-to-Formula（TTF）模型的搭建、训练与部署周期从数天缩短到数小时。该团队每两到三周微调一次基于 Llama 的模型，此前引入微调模型已使端到端延迟降低约 60%。训练流程与 MLflow、Lakehouse 治理环境打通，无需单独维护 GPU 栈。

从优化代码库到创意写作，以下是 @TulseeDoshi 和其他 Google 团队如何使用 Gemini 4 Argon 👇

Why do 200-line agent prompts, Asimov's Three Laws, and sequential pre-landing checklists all fail the same way? How Fernando Flores's 1986 Committed Speech, Nuel Belnap's 1977 4-Valued Logic, and Tony Hoare's 1978 CSP turned our Makefile …

LangChain 发布博客，介绍其开源 Agent 框架 Deep Agents 如何用 middleware 做上下文工程，应对长任务中的 context rot。

我们撰文介绍了我们的沙箱平台如何支撑 Perplexity 上的每日流量，每天处理数百万次执行，错误率很低，同时仍使用多台机器来降低服务成本。

我们的沙箱 SPACE 每天处理数百万次执行，错误率低于 0.0002%。 我们分享了它如何使用加密身份，在沙箱暂停、恢复和迁移时，确保请求与正确的执行绑定。 阅读更多：https://www.perplexity.ai/hub/blog/how-space-routes-requests-to-the-right-sandbox-execution

Every 创始人通过亲历 GPT-5 测试和对 Embiricos、Sottiaux、Glaese 等核心成员的访谈，复盘 Codex 从 2025 年 5 月 Codex Cloud 发布遇冷，到转向本地 CLI 和编辑器扩展、再到 2026 年 2 月桌面版发布并最终在 7 月并入 ChatGPT 的全过程。

a16z 合伙人 David Haber 撰文认为，长时程 Agent 已能跨数十个步骤、数周数月承接完整客户旅程，如保险理赔、按揭和企业销售。

My entry for the Hacktoberfest Open-Source AI Challenge, Week 2 (Side Hustle). A reseller I know got...

Anekha Sokhal spent nearly a decade trading energy derivatives at JP Morgan, then came to the US on a...

AI engineers spend enormous amounts of time tweaking small things to achieve bigger gains. Energy is...

When a coding agent investigates a production bug, it might need to read a repository, query logs,...

In the high-stakes world of enterprise AI engineering, the default assumption is that reliability...

Deeply understand the task at hand The biggest mistake teams make with agents is...

In audit, the opinion is the product, and an opinion is only as good as its basis. Being right isn’t...

Have you ever told your AI agent something important, only to realize a few conversations later that...

By Ryan Swift Yesterday, Google finally released its Gemini 4 Argon model for public use. It’s...

A scan of the Slack channels for a recent private equity deployment of Clonal (our operational...

Google mapped the complete male fruit fly brain, and my first question to an agent was “Can this run...

We spent the past few months on a question that sounds simple: what does it actually take to move a...

Many engineers rightfully view every step in a financial workflow as a potential point of failure,...

For financial technology institutions operating at enterprise scale, the initial wave of Generative...

The biggest design shift of the AI era isn’t about who writes the code. It’s about how long the code...

Getting an LLM-powered feature to work in a demo takes an afternoon. But getting it to produce the...

Someone built a torture chamber for small AI models, and the internet wanted it gone. I went through...

Imagine spending weeks agonizing over every single paragraph, polishing every example, and pouring...

Databricks 演示通过系统性性能优化，将 Qwen 3.8 27B 在 AI Runtime 上的微调时间从 7 小时 44 分钟降至 1 小时 17 分钟，提速 6 倍。

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle ...

Intro AI Avatar is a free app where your VRoid (VRM) avatar cheers you with all its...

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle ...

The best thing I shipped last year was a diff that deleted more than it added. I don't mean that as...

Google's Agent Development Kit (ADK) is a code-first framework: you write a Python module, declare an...

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle. ...

I gave an AI agent a Terraform task. It found a credentials problem. Part 1 of 3 in...

Two months of full-time work went into this. The part that nearly sank it was not the routing layer,...

Claude 工程负责人 Felix Rieseberg 发布教程，认为 AI 能力已跑在人的想象力前面，瓶颈是人不敢要。他把更有雄心拆解为高度、深度、广度三类：追问目标背后的目标、逼模型用顶级专业工具并以外部裁判验证、把名词还原成动词以调动更多领域，并强调需给模型电脑、装软件能力和数据访问权（如 MCP）作为前提。