AI 教程与实战

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...

Apartments.com has integrated its listing experience with Google Gemini and ChatGPT, allowing people...

GitHub Copilot 应用重建了 pull request 视图，以应对超大 diff 与评论对话带来的渲染压力。团队用一个含 2,200 个文件、超 100 万行改动、400 多条行内评论的开源 PR 做验证，将文档高度拆成确定性的代码几何与按需测量的动态块几何两部分，避免评论高度变化引发滚动跳动。

When people say we need an open standard for agent identity, I usually agree. The harder question is...

A hands-on experience report on a structured, repeatable, AI-assisted development approach We...

Fraud investigation is rarely a single-query problem. A suspicious transaction may look normal in...

Everyone eventually wants to build their LLM eval set from real traffic. It's the right instinct —...

Live replay of a dead-letter message is a control-plane act. Free inference should not own it. A...

Building an agentic fraud investigator on a 590,742-transaction TigerGraph, what a 0.963 AUC actually measured, and the number we had to withdraw.

OpenAI says its products now reach more than 1 billion weekly active users and 2.5 million...

A pull request stalled on a quiet screenshot from an agent session that looked like performance...