标签：#t

Most Chromebooks ship with only 8GB of RAM, which is enough for some people, but certainly not enough for me. Multitaskers who want more memory in their next Chromebook should check out Best Buy, which is discounting Acer’s Chromebook Plus Spin 514 for the remainder of the day. Originally $749 for the configuration with 12GB […]

Boox's new Tile lineup will take on Xteink's popular e-readers that are small enough to stick on the back of an iPhone with MagSafe. As spotted by Good E-Reader, the first one is the Picco, which will feature a 3.97-inch front-lit, black-and-white e-paper display and expandable storage with an SD card slot. Boox confirmed to […]

The AI “startups” worth billions of dollars are raising alarm bells about Chinese AI. The smaller players have a totally different take.

Following its Unpacked launch event for the Galaxy Z Fold 8 series, Samsung briefly opened a theme pub in the middle of London.

This is Optimizer, a weekly newsletter sent from Verge senior reviewer Victoria Song that dissects and discusses the latest gizmos and potions that swear they're going to change your life. Optimizer will be taking a two-week break and will be moving to Wednesdays starting August 12th. Opt in for Optimizer here. My For You page […]

Rule would allow states to decide how much—if any—public input there can be.

ChatGPT Voice on desktop can work with both ChatGPT Work and Codex to complete tasks and control agents.

Modern EV batteries aren't just holding up, they're outperforming what was expected.

Jörg Schad explains how to tame the complex "data management hairball" to build scalable, safe architectures for AI. He shares how autonomous data products act like containers for data, encapsulating pipelines, schemas, and metadata. Discover how progressive tool discovery via protocols like MCP limits context rot, enforces governance policies, and ensures reliable, multi-modal access. By Jörg Schad

GitHub热门项目 | Self-hosted audiobook and podcast server | Stars: 13,677 | 111 stars this week | 语言: JavaScript

GitHub热门项目 | A network diagnostic tool | Stars: 7,361 | 56 stars today | 语言: Rust

GitHub热门项目 | Modern server management panel built with Rust and React. Sites, databases, Docker apps, Git deploy, mail, DNS, monitoring, backups, and security — all in one panel. | Stars: 467 | 13 stars today | 语言: Rust

GitHub热门项目 | Route, manage, and analyze your LLM requests across multiple providers with a unified API interface. | Stars: 1,456 | 6 stars today | 语言: TypeScript

GitHub热门项目 | Crawlee—A web scraping and browser automation library for Node.js to build reliable crawlers. In JavaScript and TypeScript. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with Puppeteer, Playwright, Cheerio, JSDOM, and raw HTTP. Both headful and headless mode. With proxy rotation. | Stars: 24,963 | 69 stars today | 语言: TypeScript

GitHub热门项目 | 💾 Self-hosted online file converter. Supports 1000+ formats ⚙️ | Stars: 17,911 | 240 stars today | 语言: TypeScript

GitHub热门项目 | High performance Node.js image processing, the fastest module to resize JPEG, PNG, WebP, AVIF and TIFF images. Uses the libvips library. | Stars: 32,496 | 9 stars today | 语言: JavaScript

GitHub热门项目 | 🌐 Make websites accessible for AI agents. Automate tasks online with ease. | Stars: 106,530 | 270 stars today | 语言: Python

GitHub热门项目 | FlashInfer: Kernel Library for LLM Serving | Stars: 6,017 | 6 stars today | 语言: Python

GitHub热门项目 | Pretty fancy and modern terminal file manager | Stars: 19,161 | 312 stars today | 语言: Go

There's a whole ecosystem of "agent skills" now — reusable instruction files you drop into Claude Code (or Cursor, or Copilot) to make the model write cleaner code, debug more carefully, use fewer tokens, and so on. Some of these repos have tens of thousands of GitHub stars. Almost none of them ship a single number telling you whether the skill actually does anything. That bothered me, because "adding a plausible-sounding instruction" and "adding an instruction that works" look identical until you measure them. So I built a benchmark with one rule, committed before I ran anything: No skill gets merged unless it beats both a no-instruction baseline AND a placebo prompt on its pre-registered target metric, measured on hidden hold-out tests, with accuracy not allowed to drop. Skills that fail are published anyway, with their numbers. The placebo arm is the part almost nobody runs, and it turned out to be the most important one. Why a placebo Most "battle-tested" skill collections that measure anything at all compare skill-on vs skill-off. The problem: that comparison can't separate "this skill works" from "adding any confident-sounding text changes the model's behavior." LLMs are suggestible. If you want to claim your skill did something, you have to show it beats a same-length instruction that contains no actual mechanism — just vibes. So every result here is a three-way comparison — off / placebo / on — run K=5–8 times per task per arm, in isolated git workspaces, graded by hold-out acceptance tests the agent never sees, with every raw run log committed to the repo and the README regenerated from those logs in CI. 516 runs total, all on claude-opus-4-8 . Finding 1: the placebo often made code bigger My anti-over-engineering skill ( underkill , ~20 lines) cut source LOC by -23.8% vs baseline at identical accuracy (60/60 hold-out passes). Good. But the interesting column is the placebo: a same-length "write clean, minimal, professional code" instruction didn't reduce c