Joined June 2012
Gandy Marroquin S. retweeted
Walk through the model behind memory links, the valid and invalid lifecycle states, and the difference between ordinary retrieval and graph-aware search. social.ora.cl/6016BGv2SC
1
13
844
Gandy Marroquin S. retweeted
Good numbers need context. ⚡ Ask Advisor in Google Analytics can put your performance side by side with anonymized averages from similar businesses, to help you refine your strategy with confidence. Learn more about benchmarking with Ask Advisor → goo.gle/4yX1zTv
4
17
1
132
20,489
Gandy Marroquin S. retweeted
Overwhelmed by your product backlog? Use Sheets canvas to plot raw feature requests onto an interactive 2x2 effort vs. impact matrix. Collaboratively adjust scores directly on the grid and watch items shift across quadrants to pinpoint high-impact, quick wins. → goo.gle/4yqbmkl
12
34
3
267
25,834
Gandy Marroquin S. retweeted
¡Nueva biblioteca para crear diagramas en SVG! Se llama Pele y es una alternativa a Mermaid ✓ Personalizable con variables CSS ✓ Sólo ~230KB (Mermaid es +1MB) ✓ Con renderizado inmediato Creado por el equipo de Obsidian: → github.com/obsidianmd/pele
23
125
2
1,347
37,892
Gandy Marroquin S. retweeted
Aprende a instalar y desinstalar programas en Linux desde la terminal muy fácil. #linux #kalilinux #sysadmin #comandoslinux
5
37
257
4,405
Gandy Marroquin S. retweeted
El lado del mal - De Hacker a Hacker: Fran Ramírez vs. Javier Álvarez elladodelmal.com/2026/10/de-… #entrevistas #hackers #0xWord #libros #IA #Ciberseguridad
113
1
146
4,411
Gandy Marroquin S. retweeted
Analyzing long-form video in the Gemini API just got more accurate and up to 66% cheaper. Agentic video understanding uses tool calls to fetch only the media slices your prompt calls for. Read the full developer guide ↓
19
30
12
316
31,517
Gandy Marroquin S. retweeted
Cómo enumerar y encontrar vulnerabilidades en sistemas Windows de Active Directory. #ciberseguridad #hackingetico #kalilinux #pentesting
4
50
1
203
4,017
Gandy Marroquin S. retweeted
Andrew Ng siempre en mi equipo. Algunas de las citas que ha dejado en esta entrevista el fundador de Google Brain, Coursera, DeepLearning AI, profesor de la Universidad de Stanford y uno de los mayores referentes sobre IA de la actualidad. - No habrá un apocalipsis del empleo por la IA. - Sobre el empleo: la IA solo automatiza una parte de cada trabajo, así que seguimos necesitando personas para hacer el resto. No ve ningún camino realista hacia ese 50 % de desempleo que algunos anuncian. - Sobre la escasez de talento: no faltan empleos, faltan perfiles. Dice que no encuentran suficientes ingenieros de software, ni marketers, comerciales o gente de operaciones que sean «nativos de IA». - Sobre la transformación del trabajo: muchos desarrolladores front-end se han convertido en full stack porque la IA ya hace bien la parte visual. Quienes amplían su alcance y aprenden IA se vuelven muy valiosos en el mercado laboral. - Sobre el ritmo del progreso: no cree que vayamos a chocar con un límite absoluto, pero sí que el avance será gradual durante mucho tiempo. Una IA capaz de hacer cualquier tarea intelectual humana necesitaría varios avances radicalmente nuevos, y eso podría tardar décadas. Lo ve muy improbable para 2030. - Sobre el hype de Silicon Valley: la idea del «progreso compuesto» o la automejora recursiva es, por ahora, mucho más bombo que realidad. - Sobre las universidades: el problema para los jóvenes es que el sistema educativo se adapta muy despacio. Le parece lamentable que aún se pueda acabar Informática sin haber hecho nunca una llamada a la API de un modelo de IA avanzado. - Sobre contratar: ninguno de sus equipos contrata a un ingeniero que no sepa usar un agente de programación con IA. Este verano solo contrató becarios «nativos de IA», y trabajaron de maravilla. "Los empleos existen, pero hay que arreglar el sistema educativo." La entrevista completa: youtube.com/watch?v=J-sMqnzH…
17
87
6
515
24,541
Gandy Marroquin S. retweeted
We are bringing agents to the wet-lab bench at Google Research to navigate complex biological landscapes. Learn how we are grounding agents in physical lab robotics to run fast closed-loop molecular design cycles, ultimately discovering single-digit nanomolar protein binders for cancer targets →goo.gle/4B5mMMB
110
481
117
3,695
306,050
Gandy Marroquin S. retweeted
Reconstructing ancient ruins in 3D with Gemini 4 Argon 🏛️ Using Google @Antigravity and Blender MCP, see how Gemini 4 Argon supports digital heritage preservation by turning raw, fragmented archaeological data into fully explorable 3D worlds.
22
97
5
891
55,735
Gandy Marroquin S. retweeted
If you have a full-stack app in your local environment and are ready to take it to production, this course is for you. You'll learn about container orchestration, managing environments with Docker Compose, & deployment. Along the way, Gavin also teaches you about working with Dockerfiles, testing your app, and more. freecodecamp.org/news/build-…
1
94
645
26,875
Gandy Marroquin S. retweeted
Big release here! After MCP, A2A, & AG-UI, there's another agent protocol: And this one is built for Agent harnesses: UHP (Unified Harness Protocol) is a standardized interface for running agent tasks across any agent harness, regardless of which one you use. HarnessRouter is its open-source server implementation. Here's how it works: - Your product backend sends a task + harness_id to HarnessRouter. - HarnessRouter routes it to whichever configured harness should run it. - The harness streams progress and artifacts back through HarnessRouter. - HarnessRouter returns the output to your product. Three core components handle this: - Gateway: Responses API, harness config, your model keys. - Runner: Isolated workspaces, one event stream, turn checkpoints. - Built-in tools: MCP servers, browser, database, GitHub, media. This means your agent infra becomes fully interchangeable. - Swap Codex for Claude Code without touching your product code. - Run the same task across different harnesses and compare outputs. - Add new harnesses as they emerge without any rewrites. Here's the repo: github.com/HarnessRouter/har… (don't forget to star it ⭐) The savings can be substantial. In HarnessRouter's first controlled benchmark, changing only the harness reduced cost by up to 2.1×, with the cheaper setup using roughly 53% fewer credits on the same model. And Alibaba Cloud's Qoder has already officially adopted UHP, making it available as an agent backend through the HarnessRouter API. If you want to dive deeper, my co-founder's recent article explains why model routing is not the same as harness routing, and what it takes to support multiple harnesses. It also covers UHP, the full local setup, a working API call, and how sessions and files work. Read it below.
62
102
3
570
32,838
Gandy Marroquin S. retweeted
El lado del mal - ARTCraft: El Clon de la Suite de Adobe hecho con IA en formato Open Source... para Agentes IA elladodelmal.com/2026/10/art… #Adobe #OpenSource #AgentesIA #AgenticAI #MCP #IA #IA #PDF #InDesign #ARTCraft
4
127
168
5,502
GOOGLE 🔥: Gemini 4 Argon is rolling out to Google AI Pro subscribers on Antigravity! It comes with a new dedicated weekly quota, specifically for Argon model. That was fast! 👀
We’re rolling out Gemini 4 Argon in Antigravity to paid Google AI Pro subscribers today. Demand has been incredible and we've scaled capacity deliberately to get here. We’ve rolled out a separate weekly-only Argon quota for Pro on top of the existing Gemini bucket for 3.8 Flash so you have the best of Gemini for all your tasks.
53
55
9
989
38,137
Gandy Marroquin S. retweeted
Introducing gemma.ai The new hub for Gemma, including 📚Inference and training guides 🧠 Deep visual architectural guides ‍🖼️ Online demos, even running models in the browser And a lot more to come, check it out!
46
167
13
1,353
58,012
Gandy Marroquin S. retweeted
Python Turtle The Diamond Bloom
2
31
194
19,801
Gandy Marroquin S. retweeted
Empieza sin crear cuenta. Explora lecciones y practica con dinero virtual en Bolzi. Mira cómo funciona y descárgala para Android. Educación financiera; no ejecuta inversiones reales.
🤖 Made with AI

1
3
7,633
Gandy Marroquin S. retweeted
SQL vs Pandas
3
79
1
539
13,345