X

请推荐一款能上飞机的好用充电宝

x.com/i/article/205601384371…

我做了个skill，支持飞书机器人之间稳定相互at，支持自定义停止方式，比如x轮、手动停止。并且内置了自由讨论、头脑风暴、评审、辩论4种模式。支持跨openclaw、Hermes的机器人相互at，可以试试。就算用不上，我把飞书机器人at的坑踩过了，也可以看看，哈哈：github.com/iamkentzhu/lark-b…

jason from the codex team here, heres a draft on codex maxxing and the primatives i use on a daily basis jxnl.github.io/blog/writing/… would love any feedback

This might be the easiest viral AI edit yet. PixVerse → upload a selfie → instant Korean baseball cam video No prompts. No editing. Just one click. The K-Baseball Sprint template on @PixVerse_ is wild. Video

if you guys come to @aiDotEngineer Singapore i will personally lead a tour to the best cai fan i know! may 15-17 still recruiting a couple speakers, dm if mutuals and want a VIP tour of 🇸🇬

xAI 算法开源后，解读内容铺天盖地。 我敢说一句颠覆多数人认知的实话： 市面上 95% 的分析，是 AI 批量生产的同质化废话， 连源码文件名都没翻过一次。 「多互动」「多发帖」「账号要垂直」 这种谁都会说的话，说了等于没说。 真正藏在 xAI 算法深处的机制， 大多数人连名字都没听过， 却在教别人怎么运营 X。 你见过哪篇解读，是真的牛逼有价值，欢迎推荐！ 如果没有我就来个收费的文章😁 绝对牛逼！ 开玩笑，我也是每天在一点点的啃~~ 但是真的惊喜不断！

x.com/i/article/205200616280…

写了一个微信读书可视化报告skill：yao-weread-skill，已开源到GitHub 它可以把微信读书数据，生成一份本地可视化读书报告，包括： 1、近2年阅读时长与节律 2、书架书籍分析 3、阅读分类、作者、出版社偏好 4、笔记、划线、想法语义分析 5、词云、热力图、雷达图等 26 个图表 GitHub地址： github.com/yaojingang/yao-op…

New Google paper: A forecast needs context, not just history. Some patterns are caused by events, not time. Nexus reframes forecasting as a reasoning problem, where events and numbers have to explain each other. Nexus argues that forecasting improves when models read the world around the numbers, not just the numbers themselves. In the Zillow tests, one Claude-based version cut average MAPE by 86.6% versus direct chain-of-thought prompting. That matters because most time series models are fluent in pattern, but mute about cause. A housing inventory curve can reflect seasonality, mortgage pressure, migration, layoffs, and local supply, while a stock price can be bent by earnings, regulation, hype, and fear. Nexus separates those jobs instead of asking one prompt to do everything. One agent turns messy historical text into a clean event timeline, one reads the broad regime, another tracks local shocks, and a synthesizer reconciles them with calibration from past errors. The interesting result is not merely that context helps, but that structure helps the language model use context without losing the time series. The evidence is still narrow: Zillow counts, seven equities, post-cutoff data, and single-run evaluations, so this is not a universal law of forecasting. But the direction is clear: future forecasters will not only extrapolate curves; they will argue about what made the curve move. ---- Paper Link – arxiv. org/abs/2605.14389 Paper Title: "Nexus : An Agentic Framework for Time Series Forecasting"

🚨 New Gemini App UI Update This looks so cool 🤩 like I love it , btw use Gemini flash it's routing to Gemini 3.2 Everything is updated in the app , here is your first experience Video

Yann LeCun says that within a year to 18 months, we'll have a general method for training hierarchical world models These models would learn from video and real-world data, then help plan actions in robotics, healthcare, and other areas "then scale them toward a universal world model" Video

x.com/i/article/205490472266…

We're live Man vs. Machine nitter.net/i/broadcasts/1aJbdbgeA…