Your curated collection of saved posts and media
Gave codex my plasmid design notebook and asked it to animate the two key proteins doing their thing, for a video explanation I'm working on. Pretty much nailed it! Fun to wake up to work done :) https://t.co/nmE8D0ZXxj
Love this one even more. All done with Hermes Agent. cc: @Teknium @NousResearch https://t.co/Os46eK7lV7
Love this one even more. All done with Hermes Agent. cc: @Teknium @NousResearch https://t.co/Os46eK7lV7
AI is entering newsrooms, but not without resistance. While it promises efficiency, critics argue it risks diluting voice, judgment and the core craft of storytelling. The trade-off is deeper than it looks. Speed can come at the cost of meaning. https://t.co/4baYjjkImS @wired @StevenLevy
@SchrodingrsBrat some people are saying https://t.co/Ivjm9rrnI6
在 Ollama 运行 hermes https://t.co/yU4ywysy5Z
在 Ollama 运行 hermes https://t.co/yU4ywysy5Z
Hermes Desktop v0.5.0 – native Mac app for Hermes Agent. SSH only. multi-profile + full cron manager, now live ✅ NO gateway, NO daemon, remote is source of truth. The official dashboard just shipped too – great for browser admin! @Teknium @NousResearch https://t.co/19mgR9Aoi7
Trying to write a tutorial for hermes, anyone interested? https://t.co/eZDnEgtZGy
Trying to write a tutorial for hermes, anyone interested? https://t.co/eZDnEgtZGy
@trendingbots @SkylerMiao7 @MiniMax_AI https://t.co/zJpv3eIMWC
🚀 Excited to share ViPRA: Video Prediction for Robot Actions 📍 Accepted to #ICLR2026 @iclr_conf 🏆 Best Paper — #NeurIPS2025 Embodied World Models Workshop Robot learning today still needs millions of action labeled videos. Yet videos are abundant — from humans and the web — but lack action labels. Meanwhile, pretrained video models already learn rich dynamics. ViPRA is a recipe for turning pretrained video models into robot policies while enabling robot learning to scale with actionless videos. 🧵 Thread ↓
@0xViviennn Merged! https://t.co/h9grjwm8ua
在用 Hermes Agent 的时候,一直感觉跨 session 的中文搜索不太好用。Agent明明说过的话,session_search 就是搜不到,像完全失忆了一样.... 比如昨天搞了一天的A2A通信,但今天再搜"和其他Agent的聊天记录"的时候,返回 0 条结果。但数据确实在数据库里——用 LIKE子串匹配能搜出 20 多条 然后我让 Claude Code 帮忙查了一下,原因是 SQLite FTS5的默认分词器。英文有空格,天然能按词分 中文没有空格,FTS5把每个汉字当成独立 token。搜"记忆断裂"实际执行的是 记 & 忆 & 断 & 裂——四个独立的字分别匹配,丢失了词的连续性,搜不到原本存在的内容 日文、韩文也一样,都没有空格分隔,都会中招,但英文用户完全不受影响。 目前的解决方案是 FTS5 搜不到结果时,检测到查询包含 CJK 字符就自动降级到 LIKE子串匹配。比 FTS5 慢一点(全表扫描),但对 agent 的数据量完全够用。 已提 PR: https://t.co/QgT9roKg6P @NousResearch @Teknium

Thanks to our incredibly community and Viviennn in particular, we have greatly improved session-based recall for Chinese users! Thanks for the contribution! https://t.co/h9grjwm8ua
在用 Hermes Agent 的时候,一直感觉跨 session 的中文搜索不太好用。Agent明明说过的话,session_search 就是搜不到,像完全失忆了一样.... 比如昨天搞了一天的A2A通信,但今天再搜"和其他Agent的聊天记录"的时候,返回 0 条结果。但数据确实在数据库里——用 LIKE子串匹配能搜出 20 多条 然后我让 Claude Code 帮忙查了一下,原因是 SQLite FTS5的默认分词器。英文有空格,天然能按词分 中文没有空格,FTS5把每个汉字当成独立 token。搜"记忆断裂"实际执行的是 记 & 忆 &
Hermes 一丢 Agent,全网又卷出 5 个新进化体! Nous Research 的 hermes-agent(96k+ stars)底层太能打了:持久记忆 + 自动提炼技能 + 跨会话成长,社区直接当 DNA 疯狂 remix。 Atlas 上已经 90+ 项目,这次我挑了5 个最新最炸的进化体(全避开老面孔),AI 玩家看了会沉默,Agent 爱好者看了会原地 fork: 1️⃣ hermes-webui(https://t.co/EYpeGa1g4w) 浏览器/Web + 手机端 UI,把 Hermes 进化成“随时随地指挥”的 Web 版。暗黑风响应式,X 上直呼“手机党终于翻身了!” 2️⃣ hermes-dashboard(https://t.co/Y3insgftNF) 实时 Web 监控台 + 自动 Wiki:多 Agent 并行、工具调用、灵魂状态一屏看尽,还把 memory 自动转知识库。生产环境标配,Atlas 安全审查通过! 3️⃣ hermesclaw(https://t.co/WJzA56oSjv) 官方主 repo 重点推的 WeChat 桥接器,让 Hermes 和 OpenClaw 共用一个微信号,双向无缝。中文玩家狂喜:“微信生态直接被 Hermes 入侵!” 4️⃣ hermes-hudui(https://t.co/V3AZcUQCVK) 原 TUI HUD 的 Web 进化版,浏览器里实时看 Agent “在想啥”、持久记忆流动。灵魂监控 2.0,推特名场面:“终于看到 Agent 的内心戏了”。 5️⃣ awesome-hermes-agent(https://t.co/2QVFSb4Dlb) 社区维护的“进化树索引”:技能、插件、集成、教程全收录(已近 900 stars)。Atlas 列为 Guides 头牌,想 fork 就从这里抄作业。 🟢 为什么这些新项目这么爆? Hermes 从不给你黑箱,它给的是可 hack、可扩展、可自我改进的底层循环。你 fork 它,不是在用工具,而是在和 Agent 一起递归长大。 2026 年开源 Agent 的正确姿势,就是把 Hermes 当骨架,自己长肉!
Hermes 一丢 Agent,全网程序员集体进化了! Nous Research 扔出 hermes-agent(90k+ stars),核心就一个词:自我进化。它不是玩具,而是带持久记忆、自动提炼技能、跨会话成长的底层骨架。 结果?社区直接把它当 DNA,短短几周卷出 80+ 进化体,生态总星 10 万+。这才是开源的最高境界:一个 Agent,变成全世界的进化树。 我挑了 4 个正在 X 上刷屏的 “Hermes 系进化体”,AI 玩家看了会沉默,爱好者看了会狂喜: 1️⃣ Hermes Ecosystem Map / Hermes Atl

Anthropic’s Claude Mythos is drawing attention for its advanced capabilities. The model is reported to outperform humans in certain cybersecurity and hacking-related tasks, raising concerns among regulators and institutions about potential misuse. The risk is clear. As AI becomes more capable, the line between defense and offense becomes harder to control. https://t.co/v7tig74Aw9 @bbcnews @liv_mcmahon @joetidy @bbctech
The game has really changed in animation. This is my latest project Kyōdai (きょうだい ) AKA → "Siblings." An AI film concept I'm developing @promise_ai While not perfect by any means, tools like Seedance 2.0 allow for rapid prototyping and visual look development. Once explored, we bring in artists to hand draw and create the world to build and protect the IP. The VFX artist to build out the world with a hybrid 3D and AI methodology. This is the world we live in. What a time.
@LinusEkenstam Yes and https://t.co/kiuZ7QXLzb has all the good stuff from X
TBPN asked me how Zapier keeps AI from drowning in data. Short answer: we built it a brain. Three layers: 1. Company-level source of truth (strategy, values, ICP). Curated by me and a handful of senior leaders 2. Team-level context that cascades down 3. Individual context, private to each person. Meeting transcripts, Slack threads, project docs, etc. So when anyone at @Zapier talks to AI, they're not starting from scratch. They point the SDK at specific documents against the backdrop of that brain. Better inputs, better AI. Thanks to @TBPN for having me on
Hermes Agent Skin of the day. short story: i grew playing in ms-dos as a young kid. colors are different just to be easy on the eyes. https://t.co/9heRlno28L

Tonight I hung out with an entrepreneur who is building https://t.co/1tXBvxF3GP Datacenters in Space. He is putting 42,000 up over next few years. All put in space by @SpaceX And all packets will go through @Starlink. GPU inside made by @nvidia. He said the Vera Rubin set of GPUS on board is 1,000x better than the 4090 in my son’s computer. Solar cells paper thin. No air in space. First one up in six to nine months. Right next to him is another company with one of the best security testing team, er hackers, who showed me their model which is even more powerful at attacking code or systems than that Anthropic model that they say is to release to us. What they told me freaked me out. They are hacking a bunch of San Francisco startups and found critical weaknesses in most of them. And these are run by great computer scientists. They found the situation is even worse in none-tech companies. Having those hackers on the good side gives us a chance to close the holes. The founder used to be on the bad side and spent time in jail because of that. I pray every company reads and responds to their emails. I get more why Anthropic is scared about the power of the coming models. And in the kitchen was another team that has built a strategy AI they are using at Shell to predict risks to that company. This is why people love San Francisco. Me included. It is a magic place that is trying to use AI for good. Can you figure out what residency I ate dinner at tonight?
My GitHub repo has 30 stars. Mempalace has over 19000 But I just destroyed them. This is free to download by the way there’s no need to buy the coin. https://t.co/kY2eCIYNXo https://t.co/FirdAe1snA

Anthropic CEO Dario Amodei: “50% of all tech jobs, entry-level lawyers, consultants, and finance professionals will be completely wiped out within 1–5 years.” https://t.co/sXcT59gWYj
AI is starting to change even the most abstract fields. In mathematics, it is already helping prove new results at a pace that was not possible before. This may be just the beginning. AI is not only applying knowledge, it is starting to expand it. https://t.co/C9XeWKEtm9 @QuantaMagazine
Is this a model or cake? Shout out to the GDM team for inviting me to bake for Gemma4, congrats on the launch! @GoogleDeepMind @googlegemma @ivanleomk @osanseviero https://t.co/sf1KrK60rg
Is this a model or cake? Shout out to the GDM team for inviting me to bake for Gemma, congrats on the launch! @GoogleDeepMind @googlegemma @ivanleomk @osanseviero https://t.co/LaCcfLRNWn
Tesla is officially launching in Estonia. The company is holding an opening event on April 24th at Ülemiste Center "Bring your friends and family to see our models, take part in the day’s activities and test drives. We will also be showcasing the Cybertruck for the first time in Estonia." Sign up: https://t.co/tG0Swp0xK8
Have you tried @PixVerse_ video on Mirrorize AI? PixVerse is a perfect match for our image generators! https://t.co/8dadkEdNfJ
LETS GOOO(it also means everything would probably be broken) https://t.co/nZQmVLZ9Nh
A 93 year old lady filmed her Tesla FSD taking her to church and her joy is the most wholesome content on the internet. Her take on Grok: "I love that lady." https://t.co/NYIUXLwFUZ
Did you know Tesla FSD was this good?
🚨 TRUMP CALLS OUT GENOCIDE IN SOUTH AFRICA “In South Africa there’s a very horrible thing going on… it’s a genocide, it’s a horrible thing… they kill people if they’re white.” Time for sanctions! https://t.co/WKi9zbyZ49