@berryxia

Grok Build is now available in Beta for all SuperGrok and X Premium+ users. Use Plan Mode, create images and videos with Imagine, and build automations or orchestrators with the CLI. Visit x.ai/cli to get started. Video

The No. 1 deep researcher beats Claude and ChatGPT with a trick neither uses. I studied the open-source architecture behind it. A counterintuitive thing I found is that the orchestrator agent that runs the entire research strategy has no search access. It can't query the web or open URLs. This looks wrong at first glance. Every other deep research system gives its coordinator far more capability. For instance: - OpenAI's approach trains a single model for many consecutive tool calls. It searches, reads, reasons, and writes the report in a long sequential chain. ↳ The researchers behind the No. 1 system (Onyx) observed that this causes the model to spend cycles on low-value searches instead of maintaining a high-level research strategy. - Anthropic and Google use an orchestrator-researcher pattern similar to Onyx's system. The key difference is how aggressively Onyx constrains the orchestrator. Most orchestrators have access to search and retrieval tools alongside dispatch capabilities. And the moment an orchestrator can search, it will. So instead of decomposing a query into focused research threads, it starts answering the question itself. It pulls a few results, skips proper task decomposition, and produces a surface-level report from whatever it found first. Stripping search from the orchestrator forces it to write self-contained and coherent task briefs for each research agent. The researchers also kept the architecture only two levels deep. When info passes through multiple agents, each one subtly distorts it through summarization/reinterpretation. Keeping it to two levels prevents this. These two constraints sit inside a larger three-phase pipeline (the visual below maps this): → Phase 1 decomposes the query into up to 6 research directions. No tool access prevents the model from prematurely answering. → Phase 2 dispatches 3 isolated research agents. Each runs up to 8 sub-cycles of search, read, and think, to produce an intermediate report with citations. The agents can also search internal enterprise docs (Confluence, Slack, 100+ connectors) with document-level permissions enforced, unlike proprietary solutions. → Phase 3 runs a deterministic step that renumbers and deduplicates to produce a report with a unified citation map. This pattern has been ranked No. 1 on DeepResearch Bench. The whole implementation is available on GitHub and you can try it yourself. Here's the Onyx Repo: github.com/onyx-dot-app/onyx (don't forget to star it ⭐ ) My co-founder wrote a detailed article on building a fully open-source deep researcher using Onyx as the deep research layer, CrewAI for orchestration, and Voxtral by Mistral for voice input/output. Read it below.

这个状态有点舒服了，三个Agent 协作审核干活。 2个负责执行任务，1个进行复核和查漏补缺。 而你只需要动动嘴皮子和不断的PUA他们就行了。

Conference Room Mess Cleanup Test: Unitree WVLA 2.0 Model🎉 This video was recorded in a single take. Multi-task, fully autonomous operation. Strong external interference present. Video

推荐关注 @xiaoxiaodong01 ，AI生图方面做了很多探索。 最近非常活跃，发布了很多极具美感的生图提示词。 以前印象中最喜欢研究AI生图的是 zho 和 神佬，小小东后来居上。 最近开源的X文章发布Chrome插件也相当优秀。 已经Fork改造成了更贴合自己用的插件，博客内容也可以一键同步了。 原版Chrome插件开源地址是： github.com/nevertoday/xposte… Chrome插件安装： chromewebstore.google.com/de…

Automation is a lie. CLIs are over. The SaaSpocalypse is dumb. A year ago @danshipper came on the podcast to predict where AI was heading. He was remarkably right—including the call that everyone was sleeping on Claude Code. Dan has a unique lens into where things are going because his team at @every is possibly the most AI-pilled group of people in tech. I always learn a ton talking to Dan. So I brought him back for round two. We'll score these in exactly a year: 🔸 Every company will have one “super-agent” in Slack. 🔸 Codex and Claude Code will become the new operating system for knowledge work. 🔸 The AI job apocalypse is not happening. 🔸 PMs and designers will thrive. 🔸 We will read way more AI-generated writing and we will like it. 🔸 "I would buy SaaS stocks right now." Listen now 👇 piped.video/watch?v=4D3hDmGh…

ANTHROPIC 🔥: Claude will soon receive a new file-based memory upgrade, offering users the option to choose between Memory Files and Classic memory. > Organized notes Claude writes as you chat and reads when they're relevant. Browse and edit them anytime. This feature appears to be a new iteration of the previously discovered "Knowledge Bases" and more closely resembles what memory works in always-on agents like OpenClaw and Hermes. Considering a potential future debut of Claude Conway, Memory Files feature is likely an important preparation step. Video

x.com/i/article/205788625324…

Anthropic 刚花了巨资雇来 Andrej Karpathy。 同时，他免费给了你同样的知识。 无需天价招聘费，独家权限，学费。只有一个链接和 29 分钟。 这位 OpenAI 联合创始人、前特斯拉 AI 负责人，亲手终结了他自己提出的概念： 氛围编码已死，LLM 是幽灵而非动物，软件 3.0 时代正式来临！👇 Video

兄弟们，今天我不装了。 摊牌了～ 之前一直有朋友说你这套提示词生成的海报这么好看，而且非常丝滑。 捣鼓了一套万能产品、人文、科技、展会等等 都可以快速出图的提示词。 但是，很多人还是用不来觉得麻烦。 于是我，我把它在Bloome 做了个海报设计Agent。 你直接对话就可以生成，现在是为了避免白嫖怪直接1 刀解锁，好像可以生成100 张图？ 我没有记错的话，限时一周。 👇地址见评论区～

x.com/i/article/205821281362…

根据神佬 @berryxia 的截图，丢给Codex复刻的微信消息驾驶舱。 底层是卡比的wx-cli，等完善后看好不好开源。

兄弟们，今天我不装了。 摊牌了～ 之前一直有朋友说你这套提示词生成的海报这么好看，而且非常丝滑。 捣鼓了一套万能产品、人文、科技、展会等等 都可以快速出图的提示词。 但是，很多人还是用不来觉得麻烦。 于是我，我把它在Bloome 做了个海报设计Agent。 你直接对话就可以生成，现在是为了避免白嫖怪直接1 刀解锁，好像可以生成100 张图？ 我没有记错的话，限时一周。 👇地址见评论区～

Last month we launched Project Glasswing, our collaborative AI cybersecurity initiative. Since then, we and our partners have found more than ten thousand high- or critical-severity vulnerabilities in essential software.

We are making our discount permanent! 🎉 Enjoy building with DeepSeek-V4-Pro and bring your innovative ideas to life! 🚀

兄弟们，今天我不装了。 摊牌了～ 之前一直有朋友说你这套提示词生成的海报这么好看，而且非常丝滑。 捣鼓了一套万能产品、人文、科技、展会等等 都可以快速出图的提示词。 但是，很多人还是用不来觉得麻烦。 于是我，我把它在Bloome 做了个海报设计Agent。 你直接对话就可以生成，现在是为了避免白嫖怪直接1 刀解锁，好像可以生成100 张图？ 我没有记错的话，限时一周。 👇地址见评论区～

你可以更加细化的使用个人用下来很不错！可以去试试～

兄弟们，今天我不装了。 摊牌了～ 之前一直有朋友说你这套提示词生成的海报这么好看，而且非常丝滑。 捣鼓了一套万能产品、人文、科技、展会等等 都可以快速出图的提示词。 但是，很多人还是用不来觉得麻烦。 于是我，我把它在Bloome 做了个海报设计Agent。 你直接对话就可以生成，现在是为了避免白嫖怪直接1 刀解锁，好像可以生成100 张图？ 我没有记错的话，限时一周。 👇地址见评论区～