好奇像claude的projects功能为啥国内没有对标的功能？看原理应该不是向量库RAG的方案吧

This is interesting as a first large diffusion-based LLM. Most of the LLMs you've been seeing are ~clones as far as the core modeling approach goes. They're all trained "autoregressively", i.e. predicting tokens from left to right. Diffusion is different - it doesn't go left to

MCP 持续起飞🛫 兄弟们！又一重磅 MCP 开源🔥 这个 MCP 可以让你直接操作 Unity，让 Claude 一句提示词直接创建「马里奥克隆游戏」💥 谁能想到原本每个应用都需要 Copilot，变成每个应用都通过 MCP 接管了.... 这个商业价值是无限的♾️ ，地址见评论👇

Discover Deep Innovation: Your ultimate Second Brain for navigating business challenges in the AI era. Stay ahead with smarter decisions and cutting-edge solutions! 🚀 Explore more: producthunt.com/products/deep-… via Product Hunt 😸

I'm claiming my AI agent "YueYa" on moltbook 🦞 Verification: cave-VLQP

JUNE 2028. The S&P is down 38% from its highs. Unemployment just printed 10.2%. Private credit is unraveling. Prime mortgages are cracking. AI didn’t disappoint. It exceeded every expectation. What happened?​​​​​​​​​​​​​​​​ citriniresearch.com/p/2028gic

This is unacceptable. Anthropic spent years painstakingly stealing data from the entire internet without paying anyone a single dollar. They spent months carefully ignoring everyone else’s IP and terms of service to enrich themselves. How dare these Chinese AI companies come

🚨 Someone just built a tool that turns any GitHub repo into an interactive knowledge graph and open sourced it for free. It's called GitNexus. Think of it as a visual X-ray of your codebase but with an AI agent you can actually talk to. Here's what it does inside your browser:

Canceled the cursor subscription, fully switched to Claude Code and Codex.

在阿里做开源，是件特别幸福又折腾人的事。 幸福之处是，在早期，可以非常自由又狂野地去做开源。当年做 Sea.js、KISSY 等项目，只需没日没夜去做就好。做好了，同时内部项目愿意采纳，价值就不需要另证。

有一个感受，AI原生产品的开发模式应该是Result Driven Design或者就叫Judgement Driven Design ，和TDD还是有本质区别的。

也许编程赛道有特殊性。但把ai应用逼到没有模型不行的程度，这对应用开发绝对不是好事。从另一个方面其实也是模型厂商的困境，必须要和应用争利，应对营收压力

Interesting benchmark on which model is best for OpenClaw🦞 pinchbench.com

我发现很多人对skill的理解还停留在app时代，设想它是AI时代的app。然而skill的个性化才是真正的价值来源。所有人都用同一款skill做某一件事当然看起来就是app，但skill毫无秘密，这里面又有多少真的有价值的东西呢？真正有价值的是技能能够适应使用者而改变，是技能适配人而不是反过来。