Loading video...

Video Failed to Load

Go Home

Gemini 3 Flash now uses an agentic "think-act-observe" loop to solve complex visual tasks 🤖 Google DeepMind engineer Paul Ruiz demonstrates how the model runs Python code automatically to zoom and inspect items, annotate images, and re-visualize data into charts.

googleaidevs's profile picture

Google AI Developers

114,971 subscribers

106,774 views • 4 months ago •via X (Twitter)

EducationScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

🚀Excited to share that #Gemini 3 Flash can do code execution on images to zoom, count, and annotate visual inputs! The model can choose when to write code to: 🔍 Zoom & Inspect: Detect when details are too small and zoom-in. 🧮 Compute Visually: Run multi-step calculations using code (e.g., summing line items on a receipt). ✏️ Annotate: Draw arrows or bounding boxes to answer questions or show relationships between objects.
1:35

🚀Excited to share that #Gemini 3 Flash can do code execution on images to zoom, count, and annotate visual inputs! The model can choose when to write code to: 🔍 Zoom & Inspect: Detect when details are too small and zoom-in. 🧮 Compute Visually: Run multi-step calculations using code (e.g., summing line items on a receipt). ✏️ Annotate: Draw arrows or bounding boxes to answer questions or show relationships between objects.

Fei Xia

19,187 views • 5 months ago

Google DeepMind introduces Gemini Robotics 1.5, enabling robots to perceive, plan, think, use tools, and act on complex tasks. The agentic framework comprises: ⦿ Gemini Robotics-ER 1.5 (VLM): Orchestrates high-level embodied reasoning and planning. ⦿ Gemini Robotics 1.5 (VLA): Converts visuals and instructions provided by ER 1.5 into actions.
1:42

Google DeepMind introduces Gemini Robotics 1.5, enabling robots to perceive, plan, think, use tools, and act on complex tasks. The agentic framework comprises: ⦿ Gemini Robotics-ER 1.5 (VLM): Orchestrates high-level embodied reasoning and planning. ⦿ Gemini Robotics 1.5 (VLA): Converts visuals and instructions provided by ER 1.5 into actions.

The Humanoid Hub

65,928 views • 8 months ago

Join Google DeepMind Principal Engineer Adriana Porter Felt to walk through how Gemini Spark helps simplify your daily workflows. Powered by Gemini 3.5 Flash, Spark builds upon Gemini's ability to connect with Google Workspace apps like Docs and Gmail to execute complex tasks.
1:55

Join Google DeepMind Principal Engineer Adriana Porter Felt to walk through how Gemini Spark helps simplify your daily workflows. Powered by Gemini 3.5 Flash, Spark builds upon Gemini's ability to connect with Google Workspace apps like Docs and Gmail to execute complex tasks.

Google Gemini

9,617,686 views • 8 days ago

Gemini 3.5 Flash can process complex visual data and translate it into functional, interactive code. Watch Gemini analyze lighting from a reference image, and build an interactive 3D visualizer to preview the setup.
0:32

Gemini 3.5 Flash can process complex visual data and translate it into functional, interactive code. Watch Gemini analyze lighting from a reference image, and build an interactive 3D visualizer to preview the setup.

Google Gemini

499,203 views • 2 days ago

Gemini 2.5 Flash can control a browser! Excited to share Gemini Browser Agent, a simple Python script example on how to use Google DeepMind Gemini 2.5 Flash and Browser Use to act as general assistant! 🤯 Usage Examples: 1⃣ Single Query Mode: `python scripts/gemini-browser-use.py --url --query "Summarize the key features of Gemini 2.5 Flash."` 2⃣Interactive Mode: Start an interactive session, optionally with a starting URL. `python scripts/gemini-browser-use.py` Command-line options: --model: The Gemini model to use (default: gemini-2.5-flash-preview-04-17) --headless: Run the browser in headless mode --url: Starting URL for the browser to navigate to before processing the query --query: Run a single query and exit (instead of interactive mode) Time to build a replication of Manus and OpenAI Operator powered by Gemini 2.5. Code below ⬇️
0:52

Gemini 2.5 Flash can control a browser! Excited to share Gemini Browser Agent, a simple Python script example on how to use Google DeepMind Gemini 2.5 Flash and Browser Use to act as general assistant! 🤯 Usage Examples: 1⃣ Single Query Mode: `python scripts/gemini-browser-use.py --url --query "Summarize the key features of Gemini 2.5 Flash."` 2⃣Interactive Mode: Start an interactive session, optionally with a starting URL. `python scripts/gemini-browser-use.py` Command-line options: --model: The Gemini model to use (default: gemini-2.5-flash-preview-04-17) --headless: Run the browser in headless mode --url: Starting URL for the browser to navigate to before processing the query --query: Run a single query and exit (instead of interactive mode) Time to build a replication of Manus and OpenAI Operator powered by Gemini 2.5. Code below ⬇️

Philipp Schmid

105,308 views • 1 year ago

Deep Research in Google Gemini can now go beyond text to generate rich, visual reports with custom images, charts and interactive simulations. Whether you’re allocating a budget or exploring complex scientific theories, just select “Deep Research” in the Gemini app prompt bar to get started visualizing complex information. Now available to Google AI Ultra subscribers.
0:30

Deep Research in Google Gemini can now go beyond text to generate rich, visual reports with custom images, charts and interactive simulations. Whether you’re allocating a budget or exploring complex scientific theories, just select “Deep Research” in the Gemini app prompt bar to get started visualizing complex information. Now available to Google AI Ultra subscribers.

Google

153,899 views • 5 months ago

Excited to share a Google DeepMind Gemini 2.0 Flash Image Generation and Editing Quickstart. We build a Next.js reference app on how to use the new image editing feature of Gemini 2.0 Flash. Demo to test ⬇️ > Generate images from text prompts using Gemini 2.0 Flash > Or upload an image and edit it using prompts
0:48

Excited to share a Google DeepMind Gemini 2.0 Flash Image Generation and Editing Quickstart. We build a Next.js reference app on how to use the new image editing feature of Gemini 2.0 Flash. Demo to test ⬇️ > Generate images from text prompts using Gemini 2.0 Flash > Or upload an image and edit it using prompts

Philipp Schmid

52,406 views • 1 year ago

Gemini 3 Flash can analyze high-fidelity images and use multimodal reasoning to determine next steps. See how the model understands complex visuals and generates layers of interactive elements.
0:28

Gemini 3 Flash can analyze high-fidelity images and use multimodal reasoning to determine next steps. See how the model understands complex visuals and generates layers of interactive elements.

Google AI Developers

47,280 views • 5 months ago

Run Python with the Gemini API. Nikita Namjoshi shares how to use the Code Execution tool in AI Studio to solve math problems, perform data analysis, and use code-based reasoning.
4:48

Run Python with the Gemini API. Nikita Namjoshi shares how to use the Code Execution tool in AI Studio to solve math problems, perform data analysis, and use code-based reasoning.

Google AI Developers

16,481 views • 6 months ago

Antigravity's computer use has also been massively upgraded with Gemini 3 Flash. It is both faster and better at doing long agentic tasks using the browser. Here's Antigravity doing deep research on the Pareto frontier of models and writing code to visualize the result.
1:12

Antigravity's computer use has also been massively upgraded with Gemini 3 Flash. It is both faster and better at doing long agentic tasks using the browser. Here's Antigravity doing deep research on the Pareto frontier of models and writing code to visualize the result.

Varun Mohan

155,979 views • 5 months ago

I built an MCP AI Agent using Gemini Flash 2.5 with access to AirBnB and Google Maps in just 30 lines of Python Code. 100% Opensource Code.
0:40

I built an MCP AI Agent using Gemini Flash 2.5 with access to AirBnB and Google Maps in just 30 lines of Python Code. 100% Opensource Code.

Shubham Saboo

100,349 views • 1 year ago

Google drops Gemini 2.0 Flash Thinking a new experimental model that unlocks stronger reasoning capabilities and shows its thoughts. The model plans (with thoughts visible), can solve complex problems with Flash speeds, and more now available in anychat, try it out:
0:30

Google drops Gemini 2.0 Flash Thinking a new experimental model that unlocks stronger reasoning capabilities and shows its thoughts. The model plans (with thoughts visible), can solve complex problems with Flash speeds, and more now available in anychat, try it out:

AK

141,723 views • 1 year ago

Woow Google has just transformed data analysis Gemini in Colab can now plan, analyze, visualize and write Python code autonomously. This dataset of over 65,000 rows was processed without a hitch 🔥 More below
0:32

Woow Google has just transformed data analysis Gemini in Colab can now plan, analyze, visualize and write Python code autonomously. This dataset of over 65,000 rows was processed without a hitch 🔥 More below

Paul Couvert

114,132 views • 1 year ago

Multilingual voice AI tutor using the new Cartesia Sonic-2 voice model and Google DeepMind Gemini 2.0 Flash native audio understanding ...
0:48

Multilingual voice AI tutor using the new Cartesia Sonic-2 voice model and Google DeepMind Gemini 2.0 Flash native audio understanding ...

kwindla

18,793 views • 1 year ago

Build anything in the terminal with improved agentic coding in Gemini 3 Flash! Watch this demo to see how a rapid prototyping tool doesn't have to compromise code quality. Learn more about using Gemini 3 Flash with Gemini CLI →
0:52

Build anything in the terminal with improved agentic coding in Gemini 3 Flash! Watch this demo to see how a rapid prototyping tool doesn't have to compromise code quality. Learn more about using Gemini 3 Flash with Gemini CLI →

Google Cloud Tech

38,036 views • 5 months ago

⚡️ Execute sophisticated multi-step workflows and manage complex tasks with Gemini 3.1 Pro → Start building with the model via the Gemini API in Google AI Studio, @GeminiCLI, Google @Antigravity, and Android Studio.
1:06

⚡️ Execute sophisticated multi-step workflows and manage complex tasks with Gemini 3.1 Pro → Start building with the model via the Gemini API in Google AI Studio, @GeminiCLI, Google @Antigravity, and Android Studio.

Google for Developers

15,957 views • 3 months ago

Multimodal Real-Time Agents will be the future! 💯 Here is an early demo from what i am currently building! It uses Live API with Google DeepMind Gemini 2.0 Flash and React. Code will be open-source soon with a blog post on how to build your own Real-Time Agents! 🚀
1:23

Multimodal Real-Time Agents will be the future! 💯 Here is an early demo from what i am currently building! It uses Live API with Google DeepMind Gemini 2.0 Flash and React. Code will be open-source soon with a blog post on how to build your own Real-Time Agents! 🚀

Philipp Schmid

27,385 views • 1 year ago

Gemini 3 Pro in Google Search can help you quickly visualize complex topics, right in AI Mode. When you select “Thinking with 3 Pro” from the model drop-down menu in AI Mode, Gemini 3 will build a custom response to your question with visual elements so you can quickly get a richer and more helpful understanding of any topic. See it in action ⬇️
0:41

Gemini 3 Pro in Google Search can help you quickly visualize complex topics, right in AI Mode. When you select “Thinking with 3 Pro” from the model drop-down menu in AI Mode, Gemini 3 will build a custom response to your question with visual elements so you can quickly get a richer and more helpful understanding of any topic. See it in action ⬇️

Google

183,989 views • 5 months ago

Playing Pokemon with LLMs became a benchmark, but what about Super Mario? Turns out Google DeepMind Gemini 2.0 Flash can play Super Mario in real-time due to its fast latency, multimodal input and long context! 🎮 Gemini 2.0 Flash receives screenshots of the game and then generates Python code (PyAutoGUI commands) for each screenshot to control the game for a short period (the next 1 or 2 seconds). Add a while loop to it and you have it play in real-time. 🤯
1:15

Playing Pokemon with LLMs became a benchmark, but what about Super Mario? Turns out Google DeepMind Gemini 2.0 Flash can play Super Mario in real-time due to its fast latency, multimodal input and long context! 🎮 Gemini 2.0 Flash receives screenshots of the game and then generates Python code (PyAutoGUI commands) for each screenshot to control the game for a short period (the next 1 or 2 seconds). Add a while loop to it and you have it play in real-time. 🤯

Philipp Schmid

153,067 views • 1 year ago