Announcing our brand new function calling guide for @GoogleDeepMind Gemini! 🎉 We heard your feedback and made some key changes:. - New single unified guide, using the new uSDKs.- Multiple full example for Python, JavaScript and REST.- Detailed step-by-step guide.- Automatic

After JSON meta prompting for Veo, here Imagen 4! Generate high-quality json prompts for Imagen 4 using Gemini 2.5 Pro from a simple idea! Script saves prompt and images. Easy to make modification after the first version is created by Gemini. Idea: “A energy drink with water

New Hobby unlocked! Collecting custom AI silicons! 😍. Stats @ home:.✅ AWS Trainium .✅ Google TPU

Full cheatsheet:

My ultimate Gemini CLI Cheatsheet! Created a cheatsheet including all information to turn your terminal into your own personal SWE intern!. 🚀 Installation and authentication helpers. ⚙️ How to customize settings.json and provide project-specific context using GEMINI md files. 🛠️

RT @OfficialLoganK: Google is processing 980 trillion+ monthly tokens across our products and APIs (up from 480T in May) 🤯. No slowdown in….

RT @ns123abc: Bruh… people already reproduced Google’s IMO results without RL with just prompting. openai researchoors think they have the….

Check out the notebook here:

How to use the new Gemini Embedding Model with a Vector Database? @Weavite just dropped recipe notebook showing it! . Gemini Embedding supports over +100 languages, ($0.15/1M tokens), Leverages Matryoshka Representation Learning for flexible output dimensions (768, 1536, 3,072)

Gemini MCP Agent:

Here is a Gemini 2.5 Agent that connects to over 2,700 APIs and 10,000 Tools using MCP and @pipedream! It is < 100 Lines of Code! 🤯. It uses the MCP integration of the Gemini SDK, connected to Google Calendar and Gmail via Pipedream to read my meetings and send an email. Script

How good is Gemini 2.5 Flash Lite? It is really good! Here the comparison to Gemini 2.0 Flash. It costs the same but is much faster.

Blog post: Try it:

Gemini 2.5 Flash Lite now for production use! ⚡️🔦 It is the power horse, perfect high throughput uses cases! Available as `gemini-2.5-flash-lite`. - Free-Tier with 500 req/day then $0.1/$0.4 per 1M input/output token. - Supports controllable Thinking (can be turned off). -

Why did i build it: Get started:

Announcing Code Sandbox MCP, a simple code interpreter for your AI agents. Code Sandbox MCP is a simple, self-hosted code interpreter that gives AI agents like Gemini the ability to execute code in a local, containerized environment you fully control. How it works:.1. Starts a

True progress happens in partnership and with respect for each other! 🤗

Blog: Solutions:

Gold! 🥇An advanced version of Gemini with Deep Think has achieved the same level as a gold medalist in the International Mathematical Olympiad (“IMO”). - Achieved gold-medal performance, solving 5 of 6 IMO problems 35 total points.- Solved complex math problems end-to-end in

We revamped our Veo 3 guide for @GoogleDeepMind Gemini API! Focus on Developer Experience making it simpler and more examples for Python, JavaScript, Go or just curl:. - Focus on Veo 3 with Image to video coming soon. - simplified snippets for Python, Js, Go and Bash. -