juantomas (mAGIa is coming ) (@juantomas) 's Twitter Profile
juantomas (mAGIa is coming )

@juantomas

Hacking the planet Chief Envisioning Officer @sngular GDE for Cloud and ML Machine Learning Spain Meetup Co-author La pastilla Roja

ID: 870541

linkhttp://www.juantomas.net calendar_today10-03-2007 14:34:45

52,52K Tweet

4,4K Followers

1,1K Following

Rohan Paul (@rohanpaul_ai) 's Twitter Profile Photo

Github 👨‍🔧: Pocket Flow: 100-line LLM framework. Let Agents build Agents! - Build LLM applications free from external dependencies and vendor lock-in. - Implement common patterns including Agents, Multi-Agents, Workflows, and RAG based on its core graph abstraction. - Develop

Github 👨‍🔧: Pocket Flow: 100-line LLM framework. Let Agents build Agents!

- Build LLM applications free from external dependencies and vendor lock-in.

- Implement common patterns including Agents, Multi-Agents, Workflows, and RAG based on its core graph abstraction.

- Develop
Peter Steinberger (@steipete) 's Twitter Profile Photo

To understand a new codebase, my workflow: 1. Convert the repo into markdown: repo2txt.simplebasedomain.com 2. Feed that markdown into Google's AI Studio: aistudio.google.com/prompts/new_ch… Completely free and 200% faster than letting Claude run amok eating tokens. Plus Gemini has a 1Mio context

N. Taylor Mullen (@ntaylormullen) 's Twitter Profile Photo

This is truly a proud moment for me. For the past few months we've pushed non-stop to build Gemini CLI. It's been a journey, and I couldn't be happier to finally share it with all of you. Free and open source! Check it out: github.com/google-gemini/…

This is truly a proud moment for me. For the past few months we've pushed non-stop to build Gemini CLI.

It's been a journey, and I couldn't be happier to finally share it with all of you. Free and open source!

Check it out: github.com/google-gemini/…
Philipp Schmid (@_philschmid) 's Twitter Profile Photo

Gemini CLI is here! Our most powerful open-source CLI that brings Google's Gemini 2.5 models directly into your terminal! With unique features like hierarchical memory (context), self-correcting file edits, and secure sandboxed tool execution. 💡 Hierarchical Memory and

Gemini CLI is here! Our most powerful open-source CLI that brings Google's Gemini 2.5 models directly into your terminal! With unique features like hierarchical memory (context), self-correcting file edits, and secure sandboxed tool execution.

💡 Hierarchical Memory and
👩‍💻 Paige Bailey (@dynamicwebpaige) 's Twitter Profile Photo

🙌✨ You asked, you've got it: A free and open-source Gemini agent, run via the command line. And to ensure you rarely, if ever, hit a limit during this preview, we offer the industry’s largest allowance: *60 model requests per minute and 1,000 requests per day at no charge.*

🙌✨ You asked, you've got it:

A free and open-source Gemini agent, run via the command line. And to ensure you rarely, if ever, hit a limit during this preview, we offer the industry’s largest allowance:

*60 model requests per minute and 1,000 requests per day at no charge.*
Simon Willison (@simonw) 's Twitter Profile Photo

Claude Code, OpenAI Codex (CLI) and now Gemini CLI - we need a name for this category of AI-assisted terminal tools, maybe "terminal agents"?

Alvaro Cintas (@dr_cintas) 's Twitter Profile Photo

🚨 Google launches Gemini CLI. It’s an open-source AI agent that brings Gemini directly into your terminal. You can write code, debug, and automate tasks with Gemini 2.5 Pro with high usage limits at no cost.

Richard Seroter (@rseroter) 's Twitter Profile Photo

What, the Gemini CLI wasn't enough for you all today? Sheesh. Ok, how about adding agent mode to Google Cloud Code Assist? Now available to anyone on the Insiders build, you can get agentic coding (powered by the Gemini CLI) right in the IDE. codeassist.google

What, the Gemini CLI wasn't enough for you all today? Sheesh.

Ok, how about adding agent mode to <a href="/googlecloud/">Google Cloud</a> Code Assist? Now available to anyone on the Insiders build, you can get agentic coding (powered by the Gemini CLI) right in the IDE.

codeassist.google
Diego Mariño (@diegomarino) 's Twitter Profile Photo

Buenas tardes Diego. Seguro que ya estás en ello, pero sólo decirte que me encanta cuando troleas a David Bonilla. Un saludo y felicidades por tu gestión

Josh Woodward (@joshwoodward) 's Twitter Profile Photo

Calling all students in 🇺🇸🇬🇧🇯🇵🇮🇩🇧🇷 Still time to sign up and get Google Gemini App + a full year FREE of the Google AI Pro plan, do it before the June 30th deadline 👇

Calling all students in 🇺🇸🇬🇧🇯🇵🇮🇩🇧🇷 

Still time to sign up and get <a href="/GeminiApp/">Google Gemini App</a> + a full year FREE of the Google AI Pro plan, do it before the June 30th deadline 👇
Shubham Saboo (@saboo_shubham_) 's Twitter Profile Photo

This Chinese AI company trained the world's first open-weight, large-scale hybrid-attention reasoning model. MiniMax M1 has 1M context window and outperforms Claude 4 Opus in LiveCode Bench. All of this in less than $535k.

This Chinese AI company trained the world's first open-weight, large-scale hybrid-attention reasoning model.

MiniMax M1 has 1M context window and outperforms Claude 4 Opus in LiveCode Bench.

All of this in less than $535k.
javi santana (@javisantana) 's Twitter Profile Photo

I ran a claude code session to create a data pipeline with Tinybird: Total cost: $2.11 It uses best practices, almost ready to ship. I've seen people spending +100k a year on database hosting because they took a bad decision on an index

Vaibhav (VB) Srivastav (@reach_vb) 's Twitter Profile Photo

Google COOKED yet again - Multimodal Gemma3n 4B and 2B now available in Transformers, vLLM, MLX AND Llama.cpp 🤯 The model can see, hear and type - all in 140 languages ⚡ Best part: You can fine-tune it in a FREE google colab 🤗 Enjoy!

Google COOKED yet again - Multimodal Gemma3n 4B and 2B now available in Transformers, vLLM, MLX AND Llama.cpp 🤯

The model can see, hear and type - all in 140 languages ⚡

Best part: You can fine-tune it in a FREE google colab 🤗

Enjoy!
Jose Manuel de la Chica (@delachica) 's Twitter Profile Photo

Cuando más aprendo sobre IA, más me apasiona el cerebro humano. Cuanto más aprendo sobre el cerebro humano, más me apasiona trabajar en la evolución de la IA. Un eterno y grácil bucle.

Jose Manuel de la Chica (@delachica) 's Twitter Profile Photo

La teoría del cerebro basada en la estructura «descentralizada» del neocórtex en unidadades básicas columnas corticales me parece extraordinariamente útil para entender arquitecturas complejas de los modelos de IA o de agentes inteligentes. Si te interesa: amzn.to/4lxHzQw

Jose Manuel de la Chica (@delachica) 's Twitter Profile Photo

Fernando Garcia-Quismondo (高安洋) También me interesa. Pero ya sabes que me tira más ir a por lo más complejidad. Cuánto más complejo, inasible y desconocido algo, más me apasiona. Y especialmente en este campo, las analogías me parecen más útiles. Pero es verdad que es un gran matiz a tener en cuenta.