AI Coding · X Leaderboard

What is effort really? When do you change it it and why not just use max effort for everything? I dove deep into this problem, looking into evals and doing my own tests and I was quite surprised by the results. https://x.com/i/article/2103535187426709504

耶鲁一位计算机博士生，把自己发论文用的画图脚本全开源了，项目叫 figures4papers。支持柱状、雷达、折线趋势、三维球体示意、概念等类型图，8 个论文项目各一个文件夹，脚本、数据、成图放在一起，照着改数据就能出自己的图。他还把这套画图风格整理成了一个 Skill，接进 Cursor、Claude Code 或 Codex。

the reality of vibe coding agree?

The easiest way to find out which models you can run on your computer: Just run npm i -g @magnitudedev/cli and magnitude setup. It profiles your machine and ranks models by speed, accuracy, intelligence, and memory. Then pick a harness (Pi, OpenCode, Claude Code, Codex, etc.).

Cursor can now build charts and diagrams right in the chat. Use /visualize to analyze data and see the answer inline. Available now in the Agents Window. https://t.co/oDR6jJvAGK

I've tested every vibe coding resource I could find this year. These are the 28 I actually kept, grouped by what you're stuck on. Bookmark this one 🔖 🧵👇 1. https://www.scrolltide.co/ - 200+full build prompts for 3D and scroll-driven sites, each one a complete design brief rather than a component you drop in.

Welcome back to Hermes Agent, Claude New official plugin that uses Claude SDK without the tradeoffs to enable Claude Code subscriptions to work in Hermes Agent again! Check it out and install it here: https://hermes-agent.nousresearch.com/docs/plugins/claude-subscription-directsdk

After Opus 5.5, I think it's time to retire "vibe coding." This is just how programming works now.

The only Claude Code skill you need to make videos like this It analyzes your repo and outputs a complete motion-graphics teaser with sound design and launch copy in a single run. repo link: https://github.com/latent-spaces/brag

here's a prompt to improve your agent harness based on what we've learned at cursor. enjoy # Improve this agent harness's token efficiency You're working on an LLM agent harness: the system prompt, tool definitions, request assembly, context caching, compaction, and retrieval

Claude Founder House is coming to SF Tech Week (Oct 6–8) and Stockholm (Oct 14). Come for talks, workshops, and office hours with our team, plus time to meet others building with Claude. Whether you're a founder, a CEO, or a builder, there's a session for you. https://t.co/LiXccCEV7t

GLM 5.3 and GLM 5.3 Flash are now available in Cursor! GLM 5.3 Max is the best-scoring open-weight model on CursorBench 4.0. https://t.co/fEelJWzeZY

Each day, Grok Bot looks at my X Bookmarks for things I find interesting, then it spins up a Cursor Agent to build a demo. It validates work with screenshots / video, then cuts a branch on a repo configured with @Cloudflare preview deploys.

Jev Founder, Diogo Amogo, just released a PDF on building a Jev Harness for coding agents this is a blueprint on how to make your coding agents 200× faster and 400× cheaper Send this PDF and the article below to your Claude Code or Codex instance and start shipping 200× faster 👇

For those moving back to Claude Code after being on the ChatGPT/Codex app for awhile, how are you feeling about the move? What do you miss?

𝗖𝗹𝗮𝘂𝗱𝗲 𝗖𝗼𝗱𝗲 𝘁𝗶𝗽: once Opus 5.5 is your main model, don't let your Fable quota sit idle. Put Fable on call with /advisor. Run /advisor fable and Claude Code gets 𝗮𝗻 𝗮𝗱𝘃𝗶𝘀𝗼𝗿 𝗼𝗻 𝘁𝗵𝗲 𝘀𝗶𝗱𝗲𝗹𝗶𝗻𝗲𝘀. Opus 5.5 keeps doing the work and usually calls Fable in at three moments: → Before committing to a plan: is it right? → When the same error keeps coming back: am I heading the wrong way? → Before saying "done": did I miss anything? Fable reads the whole session and gives advice. Opus still writes the code.

Hot take: Vibe coding only works well if you already know how to code.

I don't think people realize you can install Claude Code inside Muse lol

The cognitive shock that devs will get in a technical loop interview after vibe-coding in their jobs for months is gonna be diabolical.

Day 100 of vibe coding 🤣 https://t.co/GRamlQMZvc