@defi2205@CarlosMaslaton Un clásico, lo hace simplemente para generar controversia, interacción, es muy poco serio, luego va a Asunción a hablar en conferencias de las maravillas del modelo, increíble.
Creo que no estás para nada interiorizado en lo que ocurre y ocurrió en Paraguay, lamentable e irresponsable análisis.
Es curioso que en tus exposiciones y charlas en Asunción no hayas mencionado nunca nada de esto no?
Has elogiado pública y sistemáticamente al "modelo Paraguayo", la fortaleza de su moneda y demás.
Sos muy contradictorio y oportunista.
I hope this is a temporary error and they restore the original reset date, because otherwise, it's a scam. In my case, it was supposed to reset next Monday, and now it resets on Friday—it doesn't make sense. They have a bug, that's understandable. They announce the fix and the reset as something positive, but they shift the original window, ruining any usage plans we've had up to now.
This doesn't make sense. I'm on the max plan of 200/month, and I did notice that my usage increased significantly in the last few hours. My weekly limit was supposed to reset this Monday at 8 PM, but now they've reset the limits, and it resets next Friday at midnight. What's the point? I think the limit "reset" is worse than the original. In fact, initially, after the reset, my weekly usage was set to reset on Monday, and moments later it changed to next Friday. it doesn't make sense......
I've been playing with OpenAI's new imagegen model for the last couple of weeks and its truly the most impressive release of 2025
Here are 10 amazing use cases 🧵
This is how 𝗔𝗜 𝗔𝗴𝗲𝗻𝘁 𝗠𝗲𝗺𝗼𝗿𝘆 works.
In general, the memory for an agent is something that we provide via context in the prompt passed to LLM that helps the agent to better plan and react given past interactions or data not immediately available.
It is useful to group the memory into four types:
𝟭. Episodic - This type of memory contains past interactions and actions performed by the agent. After an action is taken, the application controlling the agent would store the action in some kind of persistent storage so that it can be retrieved later if needed. A good example would be using a vector Database to store semantic meaning of the interactions.
𝟮. Semantic - Any external information that is available to the agent and any knowledge the agent should have about itself. You can think of this as a context similar to one used in RAG applications. It can be internal knowledge only available to the agent or a grounding context to isolate part of the internet scale data for more accurate answers.
𝟯. Procedural - This is systemic information like the structure of the System Prompt, available tools, guardrails etc. It will usually be stored in Git, Prompt and Tool Registries.
𝟰. Occasionally, the agent application would pull information from long-term memory and store it locally if it is needed for the task at hand.
𝟱. All of the information pulled together from the long-term or stored in local memory is called short-term or working memory. Compiling all of it into a prompt will produce the prompt to be passed to the LLM and it will provide further actions to be taken by the system.
We usually label 1. - 3. as Long-Term memory and 5. as Short-Term memory.
A visual explanation of potential implementation details ���
And that is it! The rest is all about how you architect the topology of your Agentic Systems.
What do you think about memory in AI Agents?
#GenAI #AI #MachineLearning
🚨 Como el robo de algunas cuentas de Telegram terminó desenmascarando el hackeo de una GRAN parte de los SMS enviados por las principales tecnológicas del mundo (Apple, Binance, Google, Microsoft, Whatsapp, Instagram, Facebook, Paypal, Mercadolibre, Telegram, Mi Argentina y más) a sus clientes en Argentina, Uruguay y Chile.
Acá va la historia (casi) completa de como se dió todo 👇
Gemini 2.5 Pro is available to all Cursor users! You can enable the full 1M context window if you'd like.
We're curious to hear how you think it compares to Sonnet.
🚀 DeepSeek-V3-0324 is out now!
🔹 Major boost in reasoning performance
🔹 Stronger front-end development skills
🔹 Smarter tool-use capabilities
✅ For non-complex reasoning tasks, we recommend using V3 — just turn off “DeepThink”
🔌 API usage remains unchanged
📜 Models are now released under the MIT License, just like DeepSeek-R1!
🔗 Open-source weights: https://t.co/DmaMLhfngk
@arielsbdar
Tienen pensado a futuro algun tipo de API oficial de Cocos? Sería interesante poder tener una api disponible, al menos para poder integrar en sistemas de trackeo de finanzas, hacer seguimiento de rendimientos, etc, quizás no tanto al principio para operar pero al menos una de acceso al portfolio y demás, sería muy útil! Hay algunas no oficiales pero estaría bueno. Saludos!
A very exciting day for open-source AI! We're releasing our biggest open source model yet -- OLMo 2 32B -- and it beats the latest GPT 3.5, GPT 4o mini, and leading open weight models like Qwen and Mistral. As usual, all data, weights, code, etc. are available.
For a long time, people have asked for an truly open-source version of ChatGPT and we finally have it. This is multiple years coming into efforts following the release of ChatGPT and builds on the efforts of so many at both Ai2 and in the broader open AI ecosystem.
With just a bit more progress everyone can pretrain, midtrain, post-train, whatever they need to get a GPT 4 class model in their class. This is a major shift in how open-source AI can grow into real applications.
Oh yeah, it's also Apache 2 as always, so happy to make things that are simple to use. I did NOT expect to be undercutting OpenAI's offerings this year but here we are :D
Google lanzó Veo 2 hace apenas 3 meses, y sigue dejando a todos con la boca abierta.
Aquí tienes 12 ejemplos increíbles (el 6 te va a volar la cabeza) 🤯👇
Chinese AI startups: 1/6th of US funding, bad press, sanctions, brain drain, communism, little English proficiency, and no talent influx..
But after using Manus AI, Deepseek, Trae, Kling, Vidu, & Ying, I think the US is in trouble.
At this pace, China will dominate AI.
Demos:
@arielsbdar Tienen pensado a futuro algun tipo de API oficial de Cocos? Sería interesante poder tener una api disponible, al menos para poder integrar en sistemas de trackeo de finanzas, hacer seguimiento de rendimientos, etc, quizás no tanto al principio para operar pero al menos una de acceso al portfolio y demás, sería muy útil! Hay algunas no oficiales pero estaría bueno. Saludos!
We've shipped several quality-of-life improvements to Cursor's UI!
We know the little bits of polish and delight matter lots in a tool that you use every day. Details below...