King2046

@libapi_ @1stsir1 👍

昨天和 Hermes Desktop 的开发者达成合作 @1stsir1 现在开发者已经加入我们一起推进。接下来会把安装体验、macOS 签名/公证、安全检查、更新机制和文档都逐步补齐。 后续会推出 Hermes Studio (桌面版) 继续保持 🔝 mac/win/linux 三端同步推出 ，敬请期待

@weiyux2021 就像配料表都是公开的，但就是吃不出“宫爆鸡丁”的味🙃

梁文峰说英伟达的显卡在技术上毫无秘密可言，那为什么偏偏是黄仁勋取得了成功?

@karpathy wow~!

Personal update: I've joined Anthropic. I think the next few years at the frontier of LLMs will be especially formative. I am very excited to join the team here and get back to R&D. I remain deeply passionate about education and plan to resume my work on it in time.

@servasyy_ai 🙃

安装了这个之后，Claude Code 的体验会完全不一样。 Anthropic 悄悄发布了一个官方插件，叫 claude-code-setup，它基本把 Claude Code 从“还不错的工具”变成了一个真正的 AI 开发环境。 它会扫描你的项目，并推荐： → hooks（钩子） → skills（技能） → MCP servers → subagents（子代理） → automations（自动化） 然后一步一步帮你把这些都配置好。 大多数人现在用的都是“原生版”的 Claude Code…… 这也是为什么他们的体验会显得有点混乱。 真正的强大之处，其实来自它周围的生态。 安装方式： /plugin install claude-code-setup@claude-plugins-official 记得先收藏，免得之后找不到。

@Kling_ai 切换自如😂

Caught this little cutie looking right at the camera.📸

@wangray 确实，目标9.9元倒推的token的套餐量

中国电信推出 Token 套餐，看到额度我笑了，这怕是没用过 AI 的人定的 好比现在推出了一个30MB的流量包月

@dotey HTML替代PPT差不多😂

其实我不太赞同文章中的观点 两者不是非此即彼的关系，Markdown 是用来保存信息，HTML 是用来展示和交互。 对于 LLM 来说，Markdown 的信息密度是最高的，HTML 是臃肿的，并不适合 HTML 阅读和生成，即使现在 AI 生成 HTML，也需要借助 React 这样的前端技术拆分成模块才能生成的比较好，一个大的 HTML 是无法一次性生成好的。

@justsosooknow 还😮‍💨🤦

某地一网红打卡地， 因为保安大叔天天看各类小姐姐前来拍照打卡， 所以， 他已经成为一名合格的摄影师了... 连动作都能进行指导了🤣

@qkl2058 胜率接近90%，怎么做到的啊🤔我这刚过50%😅

这哥们儿是个中国工程师，交易胜率接近九成，两天就赚了六万美金。 他压根不用看K线，也不用预测行情——Claude和他搭的那套六层代理系统，把活儿全干了。 优势全藏在数字和数学里头，所以他印钞一样赚钱，风险几乎为零。 说真的，现在做预测市场，你只要有AI，加上愿意动手开发，一年赚个500万美元不是梦。 大机构和那些几十亿的资本还没进场——不是不想，是声誉风险太大，这圈子现在也太早期。 所以才会有这种普通学生，把专业级别的打法用到Polymarket上。 一千笔交易赢九百笔，他吃的就是纯粹的低效率。

@bboczeng 光看模型还不够，还要看解决现实需求问题能力

操，中美模型的差距 原来是越来越大， 而不是越来越小了？

Fireside chat at Sequoia Ascent 2026 from a ~week ago. Some highlights: The first theme I tried to push on is that LLMs are about a lot more than just speeding up what existed before (e.g. coding). Three examples of new horizons: 1. menugen: an app that can be fully engulfed by LLMs, with no classical code needed: input an image, output an image and an LLM can natively do the thing. 2. install .md skills instead of install .sh scripts. Why create a complex Software 1.0 bash script for e.g. installing a piece of software if you can write the installation out in words and say "just show this to your LLM". The LLM is an advanced interpreter of English and can intelligently target installation to your setup, debug everything inline, etc. 3. LLM knowledge bases as an example of something that was *impossible* with classical code because it's computation over unstructured data (knowledge) from arbitrary sources and in arbitrary formats, including simply text articles etc. I pushed on these because in every new paradigm change, the obvious things are always in the realm of speeding up or somehow improving what existed, but here we have examples of functionality that either suddenly perhaps shouldn't even exist (1,2), or was fundamentally not possible before (3). The second (ongoing) theme is trying to explain the pattern of jaggedness in LLMs. How it can be true that a single artifact will simultaneously 1) coherently refactor a 100,000-line code base *and* 2) tell you to walk to the car wash to wash your car. I previously wrote about the source of this as having to do with verifiability of a domain, here I expand on this as having to also do with economics because revenue/TAM dictates what the frontier labs choose to package into training data distributions during RL. You're either in the data distribution (on the rails of the RL circuits) and flying or you're off-roading in the jungle with a machete, in relative terms. Still not 100% satisfied with this, but it's an ongoing struggle to build an accurate model of LLM capabilities if you wish to practically take advantage of their power while avoiding their pitfalls, which brings me to... Last theme is the agent-native economy. The decomposition of products and services into sensors, actuators and logic (split up across all of 1.0/2.0/3.0 computing paradigms), how we can make information maximally legible to LLMs, some words on the quickly emerging agentic engineering and its skill set, related hiring practices, etc., possibly even hints/dreams of fully neural computing handling the vast majority of computation with some help from (classical) CPU coprocessors.

@wangray @NousResearch @Teknium 世界从来不是非黑即白🙃🙃🙃

早就听说过 Hermes 背后是一群 Web3 原住民，但没有完整了解过来龙去脉 这篇文章整理得太好啦，适合想了解的朋友阅读 @NousResearch @Teknium do you think fair enough？

@dotey 一切工具都是手段，不是目的。

@AirdropAlchemis 😁

妈的，在soul上约了一个模特小姐姐出来见面，见面了才发现她说的modeling不是做模特，是在大厂调模型的超参数。

@NousResearch @ComfyUI 牛～！

ComfyUI is the most flexible, composable, and powerful open-source media generation tool with a massive ecosystem of workflows and custom nodes. Your Hermes Agent can now install, launch, manage, and run sophisticated @ComfyUI workflows on demand.

@RocM301 🙃

开发鸿蒙翻墙工具的团队停止更新，这团队为什么一开始会想做这个，也是神奇

@yupi996 瞬土转生之术

☘️☘️☘️

Have a great weekend everyone, don't forget to take a break from Hermes and touch some grass! We know it can be addictive

@rom1trs UGC

I built an AI Influencer automation in Arcads ... that Automatically Create UGC Videos while you sleep Comment “UGC” and I’ll send you the full workflow 👀