Jose Cuartas

[Lukas Ziegler @lukas_m_ziegler]

One of the hottest robotics courses just dropped! 🧯

Fundamentals to foundation models straight from ETH Zürich.

Everyone that has interest in robotics should dig into this course.

Whether you are an investor, a student, a robotics guy, a non-robotics guy interested in physical AI.

It's a gold mine!

The one and only @oier_mees taught robot learning at ETH Zürich this spring which was a 12-week course covering classical techniques to latest advances in large-scale models.

Syllabus covered:

→ Robot Control & MDPs, Imitation Learning, Reinforcement Learning (two weeks),
→ Generative Models, Sequence Modeling & Transformers,
→ World Models, Generalist Robot Policies, Embodied Reasoning, Frontier Problems.

Guest speakers included professors from University of Washington, Georgia Institute of Technology, Carnegie Mellon University, Google DeepMind, Physical Intelligence, Meta, and more.

All lectures were recorded and are available on YouTube. Course materials on GitHub (mees-robot-learning-course/ethz-course-2026).

Here is the course: https://t.co/VjmbAcigLp

~~

♻️ Join the weekly robotics newsletter, and never miss any news → https://t.co/GoA3ZuwoPB

[Jera ⛩ @Jera_Value]

https://t.co/I47Q8lmg4x

[PA13L0 @Fluyeporlaweb]

Tu agente de IA puede escribir código, buscar información y razonar.

Pero cuando le pides una imagen de producto profesional sale una cagada.

No porque no sepa.

Sino porque nadie le ha enseñado a pedir bien.

Este MCP le enseña.

Se llama MeiGen-AI-Design-MCP y convierte Claude Code en un estudio de diseño completo.

Le dices "crea 4 imágenes de producto para este perfume".

Sube la referencia.
Genera 4 prompts distintos.
Produce 4 direcciones creativas en paralelo.
Te las devuelve en menos de 2 minutos.

Sin salir del terminal.

✅ 1.446 prompts curados de producción real: producto, editorial, moda, arquitectura, cinematográfico y anime
✅ Compatible con Claude Code, Cursor, Windsurf, Codex, Roo Code y Hermes Agent
✅ 3 modos de backend: MeiGen cloud, tu propia clave OpenAI o ComfyUI local en tu GPU
✅ GPT Image 2, Nanobanana, Seedance 2.0, Veo 3.1 y 9 modelos más
✅ Generación paralela via subagentes - el contexto principal no se satura
✅ Offline con ComfyUI: tus imágenes no salen de tu máquina
✅ 1.4k estrellas. 181 forks. 14 releases. MIT.

La diferencia entre una imagen genérica y una de producción profesional no está en el modelo.

Está en saber pedírselo.

lo tienes abajo 👇

[YanXbt @IBuzovskyi]

HERMES AGENT + OBSIDIAN IS A COMBINATION
NOBODY IS TALKING ABOUT.

Hermes ships with a bundled Obsidian skill.
read, search, and create notes in your vault
out of the box.

why this combination is powerful:

Hermes built-in memory is capped.
MEMORY.md: 2,200 chars (~800 tokens).
USER.md: 1,375 chars (~500 tokens).

Obsidian vault has no cap.
your agent writes research, session summaries,
project context, and learned patterns
as linked markdown notes. unlimited depth.

the agent creates indexed notes by design.
timestamps, backlinks, tags.
every note connects to the knowledge graph.

three ways to integrate:

1. BUNDLED OBSIDIAN SKILL (simplest)
ships with Hermes. reads, searches,
creates notes in your vault directly.

hermes skills list | grep obsidian

2. OBSIDIAN MCP SERVER (deepest)
30+ tools: full-text search, tag lookup,
note management, vault analysis,
link analysis, orphan detection.
add it via:

hermes mcp

3. TELEGRAM + CRON → VAULT (always-on)
set a cron job that writes daily summaries,
research findings, or task reports
directly into your Obsidian vault.
your agent feeds the vault while you sleep.
you review in Obsidian when you're ready.

the unlock:

Hermes memory handles what the agent
needs to know per session (capped, injected).
Obsidian handles everything the agent
has ever learned (uncapped, searchable).

short-term in Hermes. long-term in Obsidian.
both accessible. both persistent.

keep the vault scope narrow at first.
start with one /Hermes folder.
expand once you trust the workflow.

8 Loops Indise Hermes Agent👇

[YanXbt @IBuzovskyi]

HERMES AGENT NOW HAS AUTOMATION TEMPLATES.
COPY-PASTE RECIPES FOR CRON JOBS AND WEBHOOKS.
ANY MODEL. ANY DELIVERY PLATFORM.

three trigger types:

SCHEDULE → runs on a cadence (hourly, nightly, weekly)
GITHUB EVENT → fires on PR opens, pushes, issues, CI results
API CALL → any external service POSTs JSON to your endpoint

all three deliver to Telegram, Discord, Slack,
SMS, email, GitHub comments, or local files.@NousResearch

what templates ship right now:

DEVELOPMENT:
→ nightly backlog triage (label + prioritize new issues)
→ automatic PR code review (posts review on every PR)
→ docs drift detection (finds code changes without doc updates)
→ dependency security audit (daily CVE scan, CVSS >= 7.0)

DEVOPS:
→ deploy verification (smoke tests after every deploy)
→ alert triage (correlates alerts with recent changes)
→ uptime monitor (check endpoints every 30 min,
notify only when something is down)

RESEARCH:
→ competitive repo scout (monitor competitor PRs daily)
→ weekly AI news digest (headlines, papers, repos, industry)
→ daily arXiv scan (saves summaries to your notes)

the webhook system is the part most people miss:

hermes webhook subscribe github-pr-review \
--events "pull_request" \
--prompt "Review this PR for security,
performance, and code quality." \
--skills "github-code-review" \
--deliver github_comment

one command. every future PR gets reviewed automatically.
the review posts as a comment directly on the PR.

two cost-saving details from the docs:

1. use [SILENT] in prompts.
"if nothing changed, respond with [SILENT]"
prevents notification noise on monitoring jobs.

2. use script-only cron jobs for data collection.
a Python script handles HTTP requests and file reads.
the agent only sees stdout and applies reasoning.
cheaper and more reliable than having the agent fetch.

every template is copy-paste ready.
every template works with any model.

docs: https://t.co/h4HZ0TVrYy

full Hermes agent SOUL MD guide in the article 👇

[Lukas Ziegler @lukas_m_ziegler]

Modern Robotics course for free! 📚

📍Save this for later if you are starting in robotics.

The robotics textbook "Modern Robotics" by Kevin Lynch and Frank Park is now available for free as YoutTube course.

The Specialization consists of six short courses, each taking approximately four weeks at five hours per week:

Course 1: Foundations of Robot Motion (Chapters 2-3) 
Course 2: Robot Kinematics (Chapters 4-7) 
Course 3: Robot Dynamics (Chapters 8-9) 
Course 4: Robot Motion Planning and Control (Chapters 10-11) 
Course 5: Robot Manipulation and Wheeled Mobile Robots (Chapters 12-13) 
Course 6: Capstone Project - Mobile Manipulation

The textbook covers configuration space, rigid-body motions, forward kinematics, velocity kinematics, inverse kinematics, dynamics, trajectory generation, motion planning, robot control, grasping and manipulation, and wheeled mobile robots.

Supporting materials include practice exercises with solutions, exam sets from Seoul National University (2017-2020 with solutions), video lectures filmed with Northwestern's Lightboard, software in Python/MATLAB available on GitHub.

Here's the link: https://t.co/dz4tOBdS6w
~~

♻️ Join the weekly robotics newsletter, and never miss any news → https://t.co/GoA3ZuwoPB

[Ilir Aliu @IlirAliu_]

ETH Zurich just open-sourced their entire 2026 robot learning course.

Not a MOOC. The actual course. Slides, lecture recordings, coding assignments, GitHub repo.

The curriculum goes from imitation learning and RL all the way to Vision-Language-Action models and foundation models for robotics.

Guest lectures from the co-founder of Physical Intelligence. The creator of Diffusion Policy. Pieter Abbeel. Dieter Fox.

12 weeks. Free. No signup.

If you want to understand where robot intelligence is actually heading… this is the reading list the field is using right now.

📍[https://t.co/eKsIjILi60]

——

Weekly robotics and AI insights.
Subscribe free: https://t.co/9Nm01QUcw3

[ollama @ollama]

Use Ollama with Hermes Desktop by @NousResearch.

Hermes Desktop brings the same agent (its multi-agent engine, self-improving skills, and messaging integrations) into a desktop app on macOS, Windows, and Linux.

Run it on Ollama using local or cloud with one command:

ollama launch hermes-desktop

🧵

[El Fogón de Palo🔥 @fogondpalo]

Paso a paso de la elaboración del Queso Blanco Semiduro por el chef:
👨‍🍳rafaelacostas | Chef Rafa Acosta IG

[Bécquer 🇪🇸✒🔡 @GustavoAdolf_]

Cuando se creaba música que se te clavaba en el alma. En directo y a pecho descubierto.

[Pau Labarta Bajo @paulabartabajo_]

Advice for AI engineers 💡

A small Visual Language Model fine-tuned on your custom dataset is as accurate as GPT-5...

... and costs 50 times less

For example, LFM2.5-VL-1.6B by @liquidai running locally at full speed with llama.cpp ↓

[Gabriel Castro, CFA @gabcasla]

Carta del primer trimestre de Sigma Internacional

Compartimos nuestra visión sobre la inteligencia artificial y nuestro posicionamiento en el sector de servicios petroleros.

https://t.co/X1T15l2OMF

[Emérito/Numantia Patrimonio @foso_defensivo]

"...cucha rubia, Starship colapsa el coste por kilo en órbita, eso convierte al espacio en suelo industrial para energía y cómputo, la demanda explota, y SpaceX sería un monopolio en la autopista al espacio, mentiendes?

Mira mira, con 1.000 millones de usuarios con Starlink en 2045, satélites de IA facturando $1 Trillion al año, energía en la luna, en marte y en órbita, una incipiente esfera Dyson de IA en el espacio profundo, y márgenes del 40%, sería la fucking Saudi Aramco de la galaxia, y valdría $20 Trillion, rubia, te dah cuen?

Si todo eso sale bien y el número de acciones sólo se duplica, a 2045 mis 100€ rentarán un 9% anual y...fuck, bueno tia, déjame que te cuente la increíble historia de los 1.000€ que le he confiado a Bruce Flatt..."

[Dalius - Special Sits @InvestSpecial]

Finished going through all hedge fund pitches made on this account in 2023.

Below, you'll find a list of my top 10 favorite picks that are still actionable.👇

[Oogie @oggii_0]

GPT Image 2 on @SocialSight

Prompt: A hyper-realistic macro photography shot of a giant, freestanding vintage postage stamp from [COUNTRY] standing upright against a seamless, soft, color-coordinated pastel studio background. The stamp features an intricately detailed 3D diorama of the most iconic and recognizable landmark from [COUNTRY] that pops out and actively breaks the perforated borders, extending outward into the physical space. Lush flora and fauna native to [COUNTRY] grows and spills out from the bottom right corner of the stamp's frame. A tiny, miniature figurine of a person wearing recognizable traditional cultural attire from [COUNTRY] stands on the ground at the bottom left, looking up in awe at the massive stamp, establishing a striking miniature world scale. The stamp's design includes the word "[COUNTRY]" in classic serif typography, subtext in the local language, a realistic local currency denomination, and a stamped black ink cancellation postmark in the top right corner featuring the capital city of [COUNTRY] and a realistic date. Soft, diffused, magical studio lighting with a tilt-shift lens effect and shallow depth of field. Gently floating botanical elements native to [COUNTRY] drift through the air around the scene. 8k resolution, octane render, highly detailed miniature art.

[Fazt @FaztTech]

Acabo de descubrir https://t.co/vUZktUZijp 🔥

Es una lista de las mejores “Skills” para que cualquier agente de IA genere interfaces más pulidas

✅ Animaciones que se sienten bien
✅ Accesibilidad
✅ Consistencia Tailwind
✅ Micro-interacciones de nivel pro

Si haces frontend con IA, esto es oro puro.

→ https://t.co/vUZktUZijp

[Harboris @harboriis]

GPT Image 2 on ChatGPT

Prompt:
Ultra clean streetwear graphic poster on a minimalist light gray background. Massive bold black typography reading "SOCIAL" dominates the upper composition. In front of it, oversized neon green graffiti bubble lettering spells "INTROVERT", featuring thick black outlines, glossy highlights, soft inflated shapes, hand drawn urban aesthetics, and modern street art styling.

Centered in the composition stands a realistic young streetwear model photographed from the back in a relaxed, confident pose. The subject wears an oversized vintage black graphic band t shirt, ultra baggy cargo pants with heavy folds and texture, chunky sneakers, and dark sunglasses. Hands casually placed inside pockets, creating a calm, detached, introspective mood. High contrast monochrome treatment applied to the model while the graffiti typography remains vibrant neon green, creating a striking visual contrast.

The figure overlaps the typography, producing depth and a layered editorial design. Small minimalist text above reads "MY SELF". Side captions include "SOCIAL INTROVERT" and "PERSONALITY" in clean modern sans serif typography.

Large bold headline near the bottom reads "COMFORTZONE" with a short personal statement beneath:

"I am a person who prefers to be alone and avoid crowds. Prefers to socialize in small groups. I'm not anti social but this is me."

Minimal corner crop marks, small decorative symbols, editorial layout elements, and fashion magazine inspired details placed around the composition. Bottom signature branding text reads "DREAMLAB" with a small production code underneath.

Style combines luxury streetwear advertising, modern fashion editorial design, Y2K graphics, urban culture aesthetics, graffiti typography, poster art, monochrome photography, oversized typography, clean vector elements, premium apparel branding, Instagram fashion campaign, high contrast shadows, crisp edges, professional graphic design, 4K ultra detailed, print ready quality.

Color Palette: Light gray background, deep black typography, neon green graffiti lettering, monochrome black and white subject.

Keywords: social introvert, comfort zone, streetwear poster, fashion editorial, oversized typography, graffiti lettering, baggy fashion, urban culture, luxury streetwear, modern graphic design, minimalist poster, Y2K aesthetic, premium apparel artwork, monochrome photography, hypebeast style.

[$🅰️hún @tutuflai]

Mi resumen:

El squeeze puede ser la gasolina.

Las opciones pueden ser el acelerador.

El FOMO retail puede ser la llama.

La IPO de SpaceX puede ser el foco que ilumine el sector.

Los institucionales pueden aportar validación.

Pero el motor real es otro:

Block 2 repetible.

Cadencia.

Lanzamientos.

Cobertura.

Ingresos.

Ejecución.

Si eso aparece, $ASTS deja de ser una historia bonita.

Empieza a ser infraestructura.

Y la infraestructura crítica no se valora como una promesa.

Se valora como poder.
24/n

[$🅰️hún @tutuflai]

Así que este es mi plan:

No vender por miedo.

No holdear por ego.

No fingir que voy a clavar el máximo.

No regalar mi posición por ruido.

No ignorar una valoración exigente si el mercado se vuelve loco.

Y, sobre todo, no dejar que otros piensen por mí.

Si llega la próxima ola, intentaré aprovecharla.

Como siempre:

en directo,
sin cobrar nada,
sin esconderme después,
y gratis.
Porque algunos venden grandes conocimientos.
Yo prefiero enseñar el partido mientras se juega.
Y si eres nuevo por aquí, esto es lo que vas a encontrar es una obsesión bastante poco sana por entender $ASTS antes de que sea obvio para todos.

No prometo acertar siempre.

Prometo una cosa mejor:

decir lo que pienso antes de que pase.

Porque después del gráfico, todos son genios.
La gracia está en mojarse antes.

$ASTS
25/25

[阿泽 AZe @Chenzeze777]

30 个感觉「非法」却合法的 AI 网站

1. https://t.co/nS8oupdio1 — 免费无限 AI 生图，质量直逼 Midjourney

2. https://t.co/b0SYe8RtJr — 实时 AI 生图，边画边出图

3. https://t.co/o1nscJOz24 — AI 无限放大图片，细节自动补全

4. https://t.co/19Zhv4FEae — AI 一键去背景/补光/擦除

5. https://t.co/OeeOmS3Yen — AI 语音克隆，5 秒模仿任何声音

6. https://t.co/uzUKX9sXfX — 输入歌词自动生成完整歌曲

7. https://t.co/cOtgATSrmM — AI 视频生成先驱，Gen-3 免费试

8. https://t.co/XeYeWCm913 — 快手可灵 AI，中文视频生成最丝滑

9. https://t.co/XFjLj8aqQA — 一张照片+一段语音=说话的数字人

10. https://t.co/eiUw2vW01k — 静态照片变说话视频

11. https://t.co/ZnR6eSH63U — AI 写代码，免费额度够日常用

12. https://t.co/ByaQBwfWY3 — 说话就能建网站，零代码

13. https://t.co/kdB7SQPkUU — Vercel AI 前端生成器，描述即页面

14. https://t.co/i4heLv8sjd — 浏览器里写代码+AI 辅助+一键部署

15. https://t.co/alqmH5rrik — 粘贴文字自动生成信息图

16. https://t.co/F4q6wRQjOp — AI 一键生成 PPT，告别 PPT 地狱

17. https://t.co/paZXENM42F — Notion AI 免费写+总结+翻译

18. https://t.co/F6BiyN5nVk — 画草图 AI 自动生成真实网页

19. https://t.co/9oL6AAHMMe — AI 搜索引擎，问任何问题秒给答案+来源

20. https://t.co/twj6wnQkr4 — 开发者专属 AI 搜索，代码问题一搜即解

21. https://t.co/XLa9VJIBSP — 会议实时转文字，免费每月 300 分钟

22. https://t.co/93wkAWjCHT — AI 剪辑短视频，自动找高光片段

23. https://t.co/CPWX6OWASl — 一个网站用 GPT-4 o/Claude/Gemini 全免费

24. https://t.co/LnEPgJjQ9A — 开源 AI 模型免费试玩场

25. https://t.co/ArQmpcj1CO — 一键 AI 去背景，1 秒出图

26. https://t.co/ICKoifdgUT — AI 擦除照片中任何物体

27. https://t.co/ocoZJrMrWl — AI 换脸，1 分钟出片

28. https://t.co/V6IpBEO7ll — AI 音乐标签+推荐

29. https://t.co/71HDIMW3OE — AI 写作助手，免费版够日常

30. https://t.co/RqPIAGFYez — Anthropic 免费 AI 助手，长文处理天花板

全部合法。全部免费。

在它消失前收藏这个。