wilbeibi

@istdrc Congrats !

Btw, I (previously the author of Kimi CLI) just left Moonshot AI (Kimi) a few days ago. Feeling obligated to build even more crazily.

@0xcherry 无聊才了不起

昨天春晚实在太无聊，扒拉了一会儿 OpenClaw 代码，吐槽了几句。今天有时间了，简单说一些发现吧 1. OpenClaw 内置的 Agent Loop 简单到令人发指，是用了一个叫 pi-ai 的SDK，也就是最基础的连续工具调用。 2. OpenClaw 的异步性本质还是个定时任务，也就是 30 分钟扫一次状态，并不是 event driven 之类的异步设计。可以说实际上是比较偷懒的。 3. OpenClaw 调度上的创新是 gateway 内部引入了一个主调度线程，但这个线程并没有作用在 Agent Loop 上，更多是用来给不同模块通讯用的。 4. OpenClaw 的工具看起来多，实际上核心就三个部分：浏览器操作，文件操作，cmd 操作。没了。跟 Claude Code 基本一样。 5. OpenClaw 的创新之处是他大量引入了 file 的特性在架构里，比如文件下载、截图等，这部分确实很有意思。但很多人宣称的 file driven Agent，实际看了就是个 Claude.md 等效产物，反而很无聊。 综上所述，OpenClaw 是个架构上远远没有那么“OS 级别”的 Agent，甚至最核心的 Agent Tool Loop 部分也没什么特别的。 当然，OpenClaw 的主要创新点是把一系列平时想不到的组件全都通过 gateway 连接到一起， 反而产生了奇妙的化学作用，一定程度上产生了 OS Agent 级别的“效果”，因此仍然非常有学习价值。

Gemini deserved a better product team. Skip the Chat app, just use AI Studio.

what a great agent github.com/badlogic/pi-mo…

@yucheng @steipete 太高产了

ClawdBot 的作者 @steipete 就是AI文艺复兴时代的达芬奇

@dongxi_nlp Man，这个太赞了

如何在海量 AI 论文中找到热点、机会与趋势？ 先说我的答案，Papers + Graph + Time 现在 AI 论文的产生速度极快，仅看 Hugging Face 榜单，每月上百篇，一年上千篇，问题来了，如何在海量论文中找到价值与机会？ 其实论文之间天然联系，他们的相近方法会迁移到不同问题，同类问题也会推动方法持续迭代并刷新 SOTA。 领域与方法因此形成若干 node，nodes 之间通过共享的关键论文与方法脉络相互连接，建立edge，即形成了 graph。 如果把这种 graph 与 time 叠加，就能看清热点与方法的流动，抓住当下，并推演未来趋势。 因为最近格外关注中国开源模型厂商，我把 Paper + Graph + Time 这种思路，给到 MiniMax Agent, 让它把我脑海中的这个比较复杂的工具 vibe 出来。 如视频所示，结果非常惊艳，这个工具成功带领我迅速了解了本月上百篇论文，我从中可以沿着自己喜欢的轨迹找到喜欢的话题和方向。 Kudos to @MiniMax_AI ! MiniMax Agent Desktop 非常出色，可以直接连接我本地的论文库，与cc比较，以很低的成本，做完了这个复杂度非常高的任务，点赞！ 值得注意的是 MiniMax Agent 的 expert 模式超强，而且非常好看，这对应了他们设计的专门的 benchmark VIBE Bench！ 衡量的不仅仅完成度，还有 vibe，还有外观！

GitHub devs have overflowing creativity. We should trade some for an HCI class.

Last quarter I rolled out Microsoft Copilot to 4,000 employees. $30 per seat per month. $1.4 million annually. I called it "digital transformation." The board loved that phrase. They approved it in eleven minutes. No one asked what it would actually do. Including me. I told everyone it would "10x productivity." That's not a real number. But it sounds like one. HR asked how we'd measure the 10x. I said we'd "leverage analytics dashboards." They stopped asking. Three months later I checked the usage reports. 47 people had opened it. 12 had used it more than once. One of them was me. I used it to summarize an email I could have read in 30 seconds. It took 45 seconds. Plus the time it took to fix the hallucinations. But I called it a "pilot success." Success means the pilot didn't visibly fail. The CFO asked about ROI. I showed him a graph. The graph went up and to the right. It measured "AI enablement." I made that metric up. He nodded approvingly. We're "AI-enabled" now. I don't know what that means. But it's in our investor deck. A senior developer asked why we didn't use Claude or ChatGPT. I said we needed "enterprise-grade security." He asked what that meant. I said "compliance." He asked which compliance. I said "all of them." He looked skeptical. I scheduled him for a "career development conversation." He stopped asking questions. Microsoft sent a case study team. They wanted to feature us as a success story. I told them we "saved 40,000 hours." I calculated that number by multiplying employees by a number I made up. They didn't verify it. They never do. Now we're on Microsoft's website. "Global enterprise achieves 40,000 hours of productivity gains with Copilot." The CEO shared it on LinkedIn. He got 3,000 likes. He's never used Copilot. None of the executives have. We have an exemption. "Strategic focus requires minimal digital distraction." I wrote that policy. The licenses renew next month. I'm requesting an expansion. 5,000 more seats. We haven't used the first 4,000. But this time we'll "drive adoption." Adoption means mandatory training. Training means a 45-minute webinar no one watches. But completion will be tracked. Completion is a metric. Metrics go in dashboards. Dashboards go in board presentations. Board presentations get me promoted. I'll be SVP by Q3. I still don't know what Copilot does. But I know what it's for. It's for showing we're "investing in AI." Investment means spending. Spending means commitment. Commitment means we're serious about the future. The future is whatever I say it is. As long as the graph goes up and to the right.

@tuzi_ai @dotey 不是，这个真的是同一个时空的 AI 工具做的么，一年后的 AI 有着水平我都觉得牛逼。

一个新高度，国内纯 AI 作品，热血沸腾到了；果然人的智慧不可或缺啊！ 作品名：【箭头】如果世界真的是程序，你会继续当个NPC吗 作品完全由Nano banana, veo3, runway制作，音乐是suno生成 B 站地址：bilibili.com/video/BV1RW27B…

@dotey 宝老厉害👍

Thank you, Sundar! It's truly an honor. 🙏 The magic really happens when combining Nano Banana Pro's visualization capabilities with its vast world knowledge and Gemini's live connectivity. Nano Banana Pro turns abstract ideas into reality and, best of all, empowers everyone to unleash their creativity freely.

Well, @badlogicgames reminded of the value of sharing, so here’s the update: agent building is hard. Agent SDKs are tricky, caching is a per-model art, reinforcement can help, isolation saves your sanity, filesystems! New models are “it depends.” lucumr.pocoo.org/2025/11/21/age…

刚发现，南湾图书馆的在线资源居然有完整的 Value Line 可以看。交了那么多税，总算有点回头钱了。

@yihong0618 是很好，就是 PR 没人理。

@blackanger 好主意

我有个大胆的想法： 在 claude code skill 的工具里使用codex sdk，那么我的claude code 是不是就可以使唤 codex 了

opensource.googleblog.com/2025/11/announ… 这才是软件未来来的方向，整个库就是一个 1MB 的模型加个 wrapper，真好。

@bigeagle_xd @TheInclusionAI @Kimi_Moonshot @Zai_org Great work !

Team from Ant Group @TheInclusionAI helped land Kimi model @Kimi_Moonshot on @Zai_org's slime framework! Open AIs help Open AIs ♥️ CN AIs help CN AIs ♥️

我无法理解为什么会有人类会玩永续合约。。。

@bigeagle_xd 看 kimi cli 学习到很多，感谢。

we've been challenging ourselves "does the world need one more code-cli?" "how can we catch up with claude-code?" maybe the answer is NO, but at least, we have one place to share our understanding of coding agents, and good changes will gradually happen. it's just a beginning.

@cheerselflin lol

笑死了！外国人用 cursor最新模型，结果……全世界都在学中文！

@Manjusaka_Lee 打表出奇迹

uploadcare.com/blog/faster-bl… 推荐一篇文章 BTW，我太爱我司 CTO 了，每天（字面意思）跟着他都能学到新东西