Want to chat with your Hermes Agent on iMessage without a Mac? The latest v0.17.0 update made this possible (and super easy)! I made a quick video showing how to get this all set up in less than three minutes. Enjoy! https://t.co/N0mfxHUagJ

@BeingJonG So far no major catastrophes 😂 It's cad was a little wonky but functional for my purpose. It had a bug in the code that resulted in some overextrusion but fixed it when I suggested it (2nd pic is bug). For now I've taken back control w/ codex's scripts and am having lots of fun https://t.co/YVIIMZw24j

Seems like with a little tweaking I can get some watertight ~100um channels with PLA directly on a glass slide w/ a cover slip melted on. Only had a few hours to get it going today, will tweak it and try to dial it in tomorrow. Goal: DIY microfluidic algae cell sorting! https://t.co/JQpQ3UZd0I

@TonyW @SakanaAILabs Thanks, Tony! Indeed, this was the vision from the beginning: https://t.co/D1cEX0noMl

Top AI papers on @huggingface this week: looped world models, real-time VL agents, and 3B reasoning marvels - Looped World Models — first looped architecture for world simulation, 100x parameter efficiency - LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling — 2 loops is the surprising sweet spot for code reasoning - JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence — an always-on vision agent that decides when to speak - Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories — a fully autonomous virtual newsroom - Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance — 15x faster than 10B rivals - VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models — 3B model rivaling DeepSeek V3.2 and Gemini 3 Pro - DreamX-World 1.0: A General-Purpose Interactive World Model — interactive world generation at 16 FPS - OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data — director-level camera motion control - Geometric Action Model for Robot Policy Learning — 3D geometry-native robot policies - FastContext: Training Efficient Repository Explorer for Coding Agents by @microsoft — cuts coding agent token use by 60% Find them below:

Classic short term thinking. What about the heat death of the universe? This paper shows we could survive 100 billion years past the end of all near stars, if we start building Dyson Spheres around millions of stars and start gathering them together soon. https://t.co/QM5uNAtATP https://t.co/vfeCkrTXNo

A few years ago, AI data centers in space would have sounded like science fiction. Today, serious entrepreneurs and investors are discussing them as a potential solution to growing constraints around energy, land and cooling. The most interesting ideas often start where practicality and imagination meet.

I did not think two months ago when I moved to sf that I would have met all of these very special Pokémon &shoutout to the most special Pokémon of all, my best friend, sister, and roommate for supporting me in my endeavors (she let me invite random strangers I met online into our home) @emolyonx

+2 more

Our mission is to benefit all humanity https://t.co/Qwwu6Eat0O

China added a Germany-sized low carbon electricity grid last year. Nearly 500 TWh more generation, almost all solar and wind, built in factories that still burn coal. Carbon payback came in under two years and power sector emissions still fell. Germany already had zero carbon nuclear power. It shut the last plants down in 2023 because ideology demanded it. Higher prices and more coal and gas backup followed. One country scales clean energy through ruthless pragmatism. The other commits economic suicide and calls it environmental virtue. The West is economically self-destructing by submitting to blue haired lesbians on SSRIs.

@JesseGiotti @hikariraina @ScriptedAlchemy Just choose OpenAI here: https://t.co/91jUjo1z7c

yes in case you missed it we are doing "poaster" sessions at AIE for the first time ever no papers, no posters. only poasters. we are looking for people who physically print out their hottest takes and stand in front of them taking all comers @QuinnyPig is there, we have room for a couple dozen more. application below cc @vibhuuuus

spotted in the west village: the carrie bradshaw-ification of codex https://t.co/XKZgi6fth7

spotted in the west village: the carrie bradshaw-ification of codex https://t.co/XKZgi6fth7

@itsjessyin Get that moneyyyy https://t.co/C0VptoBj1z

appshots are still one of the best features in codex https://t.co/pbxQQXkR4N

Day 1 of vibecoding https://t.co/n8ff35htEV

Human intelligence is fundamentally a collective intelligence. We solve complex problems by participating in a vast cultural network that builds upon ideas across generations. I believe the strongest AI systems will become a collective intelligence, too. Since we started Sakana AI, our core conviction has been that the most powerful AI systems will be collaborative ecosystems, not isolated monoliths. Evolution innovates under constraints, and the future belongs to systems that explicitly learn how to coordinate collective intelligence. Today, we are taking a major step toward that future with the launch of Sakana Fugu. Fugu dynamically orchestrates the world’s best models to tackle complex tasks. We are proving that a well-orchestrated pool of swappable agents can match restricted frontier models like Fable and Mythos. But Fugu is about more than just performance. I believe that Orchestration Models are the next frontier, beyond bigger models. Relying on a single company’s model for national infrastructure is a massive risk. As recent export controls have shown, access to top models can disappear overnight. Collective intelligence is the practical hedge against this concentration of power. Fugu simply routes around vendor restrictions by relying on an entirely swappable agent pool. I am incredibly proud of our Tokyo team for shipping this. By orchestrating the world’s models, we are delivering the resilient blueprint required for AI sovereignty. Read our full vision and results here: https://t.co/EONDdWx5Ld 🐡

When Elon Musk visited Pope Francis at the Vatican with his kids. https://t.co/fyqFPwUd17

There's nothing like celebrating Father's Day with your children, grand kids and great grandsons! I hope you all had a wonderful day. My best, Bill https://t.co/vfSPIJROXP

Esta semana he estado probando Hermes Agent Desktop en su versión de escritorio y está bastante interesante 👀 Pensé que iba a ser solo una app que se conectaba a un Hermes desplegado en un VPS, pero no: es Hermes completo. Descargas Hermes Desktop y te instala también las herramientas de consola, los skills, todo. Y te lo ofrece a través de una interfaz muy sencilla para que puedas hablar con un asistente personal que tiene memoria, que puedes conectar con Telegram, y todo desde tu propia laptop. En cuanto a la interfaz, se parece a otras similares como OpenCode Desktop o Codex Desktop, pero esta tiene mejor UI, me parece que la trabajaron bastante mejor. Responde rápido, es multiplataforma y puedes ponerle cualquier suscripción de modelo. También puedes ejecutar subagentes, e incluso si vas a hacer tareas de código las puedes delegar a OpenCode desde la misma interfaz ⚡Resumiendo: está bastante bien. Como app de escritorio, quizás es una de las mejorcitas que hay ahora mismo. Aún le falta varias caracteristicas que tiene Codex Desktop, pero es está bastante usable. Les dejo el enlace del sitio si quieren probarlo 👇

How does it work? Sakana Fugu is itself an LLM, trained to call various LLMs in an agent pool, including instances of itself recursively. Fugu dynamically orchestrates the world's best models to tackle complex, multi-step tasks. As shown in this figure, Fugu is a multi-agent system that behaves like a single model. You send a request to one endpoint, and Fugu decides how to handle it internally. Fugu manages model selection, delegation, verification, and synthesis automatically. It solves tasks directly when that is enough, or coordinates a team of expert models when a problem calls for more. The complexity of a multi-agent system never reaches your code. At launch, Sakana Fugu comes in two models accessed via a single OpenAI-compatible API: • Fugu balances strong performance with low latency for everyday work. It fits naturally into tools like Codex for coding, as well as chatbots and interactive services. You can also opt specific agents out of its pool for data compliance. • Fugu Ultra is our flagship model tuned for maximum answer quality on hard, multi-step problems. It coordinates a deeper pool of expert agents for demanding work like AI research, cybersecurity analysis, and patent investigations.

My @NousResearch Hermes-Agent is cooler than your Hermes-agent because mine can make t-shirts end-to-end pretty much by itself. Using design skills + GPT Image 2 Skills + Shopify/Printful skills. From concept to final product. First sample “Made with Hermes Agent” tshirt arrived for my kid. What has your Hermes-Agent shipped today?

Creating some new infographics themes with Hermes rn wdyt https://t.co/M7fKBH3WQ5

让你 Hermes 聪明十倍的记忆插件！ Hindsight仿生记忆系统（LongMemEval冠军），Hindsight本地嵌入插件、agentmemory 4层巩固插件、Hermes Workspace新Mission Control无限编排、hermes-desktop最新桌面伴侣……全网玩家把Hermes玩成了下一代「会学习的记忆大脑 + 生产级控制面 + 无限Agent舰队 + 原生桌面体验」： 1️⃣ vectorize-io/hindsight（https://t.co/L3RXrHnL5t） 仿生3层记忆，混合检索，LongMemEval 2026冠军，Hermes官方plugin。 “Agent终于会真正学习了”！ 2️⃣ vectorize-io/hindsight本地嵌入（https://t.co/L3RXrHnL5t） 解决插件依赖，本地嵌入模式完美支持Hermes。 “记忆增强直接起飞”！ 3️⃣ agentmemory Hermes集成（https://t.co/LefXP7LJk2） 4层巩固 + 43 MCP工具，95.2%检索率。 “持久记忆天花板”！ 4️⃣ outsourc-e/hermes-workspace新Mission Control（https://t.co/IjMwS0zvUn） 无限Agent编排 + 1 orchestrator + 持久tmux。 “舰队指挥官上线”！ 5️⃣ fathah/hermes-desktop最新版（https://t.co/HAwVxwUOx8） 原生桌面伴侣，支持v0.17+新特性。 “终端党终于有桌面体验了”！

+3 more

Introducing Sakana Fugu: A full multi-agent orchestration system accessible via a single model API. Our ‘Fugu Ultra’ model matches the performance of Fable and Mythos, delivering frontier capability without the risk of export controls. Try it: https://t.co/hhO6qTawgb 🐡

Fugu stands shoulder-to-shoulder with leading models like Fable and Mythos across the industry's most rigorous engineering, scientific, and reasoning benchmarks. Read the full blog: https://t.co/2ZJbdWqCUj Beyond Bigger Models: Why are Orchestration Models the Next Frontier Progress in AI has been driven largely by giant, monolithic models. But the most powerful systems of the future will be collaborative ecosystems. Today, this orchestration is no longer just a technical optimization. It has become a geopolitical and operational imperative. For an organization or a nation, relying on a single company's model for critical infrastructure, finance, or governance is a material vulnerability. This risk is no longer a hypothetical possibility, but a reality. As we have seen with recent export controls imposed on models like Fable and Mythos, access can disappear overnight. Collective intelligence is the practical hedge against this concentration of power. Because Fugu orchestrates an underlying pool of swappable agents, it simply routes around vendor restrictions. By orchestrating the world’s models, we are delivering the resilient blueprint required for true AI sovereignty.

You can self host Mem0 now https://t.co/uLbesDPS67

PR if you want the deets: https://t.co/PX0qKJKNC1

@7amud7amudi https://t.co/25mC2H0g2X

We parsed this SpaceX equity research PDF faster than the time it took for Screen Studio to zoom in ⚡️🔥 liteparse is now the best open-source document parsing tool out there. There’s no reason to not use it as a first pass, even if you do have docs that require heavier VLM processing downstream. Try it out now over any document: https://t.co/ErgwlItZ96 Repo: https://t.co/JNER0mVcB8

+1 more