lesly🍫
@leslysandra
🤖 AI + Tech + Education 🤓 Curriculum Developer @DeepLearningAI AI/Cloud GDE @GoogleDevExpert @MentorHerBo 📍De Bolivia para el mundo 🌎 #savedbygrace
Google AI Studio para Educadores, Desarrolladores y Curiosos de la IA 🌟 ... youtu.be/AGYZDTeGJRk?si… via @YouTube
Announcing our new event - Buildathon: The Rapid Engineering Competition. See the video for details, and please apply to participate!
I just published EduCreador IA: Cómo Construí un Generador de Contenidos Educativos con Gemini en 30 Minutos medium.com/p/educreador-i…
I just published Crea tu Primer Agente de IA ADK 🤖 — Agent Development Kit de Google medium.com/p/crea-tu-prim…
🥳
¡Atención, Uruguay! 🇺🇾 Prepárate para AI Gatherings Uruguay. Exploraremos la vanguardia de la Inteligencia Artificial. Conéctate con líderes, startups y desarrolladores. 🗓️ 25 de Julio, 9:30 AM - 2:30 PM 📍 ANDE, Montevideo 🔗 ¡Regístrate aquí rsvp.withgoogle.com/events/ai_gath…
IMO Gold for Gemini 🥇 using an advanced version of Gemini + Deep Think. Huge progress from last year's silver medal using domain specific models. Much more to share soon : )
New function calling guide with Gemma 3 & KerasHub -- really nice to be able to run locally.
Function calling guide for Keras!
Gemini has unlocked a new capability: conversational image segmentation 🖼️ This enables new use cases that were previously not possible, furthering Gemini’s SOTA image understanding capabilities! 🧵
Multi-agent orchestration is complex, especially when mixing languages like Python & Java. The open A2A (agent-to-agent) protocol is designed to simplify this communication between agents. Learn how to build a multi-agent Airbnb planner using A2A and ADK. ⬇️
It's official: Gemini 2.5 Flash Lite is now Generally Available and ready for your production workloads. 🚀 Our fastest, most cost-effective model comes with native multimodal reasoning and a 1 million token context window. Read my developers blog below ⬇️
RAG augments a standard LLM pipeline with a retrieval step; injecting external, often domain-specific data into the prompt before generation. This improves factual accuracy, enables source attribution, and avoids the need for expensive retraining. By decoupling retrieval from…
🗓️ ENCUENTRO VIRTUAL - 30 JUL | 12 h GMT-3 🔬 América Latina avanza hacia la #CienciaAbierta, pero persisten desafíos en indicadores y coordinación regional. 📊 ¿Qué herramientas priorizar? 👉 Sumate al debate: unesco-org.zoom.us/webinar/regist… 👉 Más info: forocilac.org/30-jul-monitor…
4 stages of training LLMs from scratch, visually explained:
4 stages of training LLMs from scratch, clearly explained (with visuals):
Google DeepMind is winning, they just don’t hype it. > Participated in IMO > IMO officials verified the solution > Awarded Gold medal > Quietly dropped the post on a Monday morning At this point, they’re not even bothered about competing. Also this version of Gemini is coming…
Adding 𝗠𝗖𝗣 to 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗥𝗔𝗚 Systems. If you are building RAG systems and packing many data sources for retrieval, most likely there is some agency present at least at the data source selection for retrieval stage. This is how MCP enriches the evolution of your…
If a picture of your pet says 1,000 words, imagine turning it into a video.
Meta Data Analyst Professional Certificate 📊 Introduction to Data Analytics 💻 Data Analysis with Spreadsheets and SQL 🐍 Python Data Analytics 📈 Statistics for Marketing 🗃️ Introduction to Data Management imp.i384100.net/4P9GQG
56 years ago today, humans walked on the moon for the first time. Original @TIME report of the monumental event, from 1969: bit.ly/3UbKiTP
Agent Development Kit: Making it easy to build multi-agent applications developers.googleblog.com/en/agent-devel…
