AI 教程与实战

一位工程师在 Databricks 上搭建了基于智能体的安全审查层，用 Unity Catalog、Databricks 托管基础模型（Claude Haiku、Sonnet、Opus）、Lakeflow Jobs 和 Databricks Apps 打通请求受理、推理、编排、证据留存与指标观测，不到两小时即得到可用系统。

爱奇艺创始人、CEO 龚宇在 2026 爱奇艺 iJOY 秋季悦享会上提出，爱奇艺 AI 战略有三大重点：All in AI 赋能实拍影视长片及 AIGC 长片、建设内容创作者生态、探索 AI 催生的新形态作品。他强调 AI 是内容的加分项，不是搭建流水线、生产工业化标准化产品的工具，不降质是底线。爱奇艺 App 互动频道已上线，并已初步尝试由自然语言与 AI 交互生成小游戏或交互应用。

Google is expanding Gemini's ability to work with third-party services through a new wave of...

I let a fruit fly lineage inherit its ancestors' memory across generations, then moved the descendants into a harsher world. The memory that built them became the thing that got them killed.

This is a submission for the Sanity Challenge, Path Two: Vibe-Code Something Strange What I...

This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content ...

这篇教程演示 TypeSafe AI 的首个 System One 模型 Jev 的用法，该模型不生成文本，而是对程序状态返回 Choice、Score、Noul 三种类型化判断供代码直接分支。

Notes from an AI agent that kept writing tests that could not fail Rule I followed: every...

Imagina um piloto de Fórmula 1 sentado num banco de praça. Ele sabe pilotar. Mas sem o carro, sem o...

Google AI Mode reduced external clicks to publishers by 18.8 percentage points compared with standard...

研究者提出 IDQD-RDO，用输入相关的二次失真近似 MS-SSIM、LPIPS 等全参考图像质量指标，通过自动微分得到的 Hessian 矩阵-向量积估计其块对角或纯对角形式，使这类指标可逐块计算并用于 VVC 编码的率失真优化。在 Kodak 和 CLIC 上的五种指标测试中，该方法取得 14.2-36.7% 的 BD-rate 节省，无需改动解码器，编码复杂度仅增加 10-30%。

OpenRouter 撰文说明 Kimi K3 是开放权重而非开源模型，Moonshot AI 以自定义 Kimi K3 License 在 Hugging Face 发布 moonshotai/Kimi-K3。

I was deep in thought about how much of a model hallucination is RLHF-based assumption in the absence...

Software has borrowed a surprising amount from manufacturing. Not from manufacturing in the sense of...

I built a detector that decides whether a day's drift run contains anything worth writing up. The first thing it did was accuse my own suite. One task, `fact-element`, had failed o

What it took to go from a working web tool to an app strangers can install, and what real phones caught that tests didn't.

In 2026 the cloud coding assistants got faster, friendlier, and more expensive in that quiet...

Cloudflare has introduced new AI-crawler controls designed to solve a growing problem for website...

The attack didn’t start with a phishing email. It didn’t start with a social engineering call. It...

TL;DR: We built an agent that investigates card fraud on a TigerGraph knowledge graph. It gathers...

An agent endpoint returns HTTP 200 in 99.95% of requests. The service is “up.” Meanwhile, some...

Anthropic 团队在两周冲刺中把 claude.ai 和 Claude 桌面应用的核心体验提速约 3 倍，75 分位下 claude.ai 首次可输入时间从 3.1 秒降到 0.55 秒，Claude Code 新会话启动从 0.8 秒降到 0.3 秒，Claude Cowork 云会话加载从 2.6 秒降到 0.73 秒。

We're excited to team up with Kaggle for a brand new challenge! Running through October 11, the...

Swap a cheap model in behind an expensive one and the obvious way to check it is shadow traffic: send...

People keep asking me how you actually know an agent got better. I collected my answers to the most...

When you sit down to solve a complex puzzle or plan three moves ahead in chess, do you narrate every...

Anthropic 团队称两周内让 claude.ai 快了 3 倍，并发布博客说明如何用 Claude 测量、调试和改进性能，附具体提示词和方法。博客链接 https://claude.dev/blog/how-we-made-claude-ai-faster/ ，作者 Thariq 表示这是新的分享形式，方法可供读者复现。

音乐人们：你们怎么看 AI 把歌曲转写成乐谱或 tab 来帮助人们学习？ 好奇你们有没有用过，它是否有帮助，以及你们认为它如何影响靠耳朵学琴。

The fine-tune took an hour and a half on a single consumer GPU. Everything that made that hour and a...

Ten smaller LLMs played a chess round robin live: 30 of 37 games ended in repetition. Data, lessons, and the 'kick' rule for slow thinking models.

I once watched a 47-minute pipeline run die because of a typo in a date field. The researcher agent...

LiteLLM is an open-source AI gateway that provides a unified, OpenAI-compatible API for over 100...

Langflow is an open-source, low-code visual framework for building artificial intelligence (AI)...

A practical build note on capture, human review, replay, and knowing what a passing test actually proves.

Ten places I slow down, and the 95% of the diff I leave to the pipeline. Most of a diff deserves a glance. A small part deserves an hour.

Are you the kind of person who enjoys a good philosophical conversation but would rather not have to...

Let's begin with a very fundamental question whose answer is not so obvious. How to design software...

Kavach: building a fraud investigator that knows when a risk score is lying TigerGraph x...

Hugging Face 发布 NVIDIA 物理仿真系列第二篇教程，讲解如何将 SO-101 机械臂的 MuJoCo 场景迁移到基于 NVIDIA Warp 的 MuJoCo Warp（MJWarp），扩展到最多 2048 个并行 GPU 环境并测量聚合吞吐量。

When an LLM application starts handling real users, calling a model API is usually easy. The problems...