Corbin Cunningham, PhD

Senior Staff UX Research Manager @ Labs | Google | Building AI-powered Products like NotebookLM

[Josh Woodward @joshwoodward]

The @GeminiApp now has the #1 image model in the world, give it a go!

Attach an image, describe your edits, and it's done

I've never seen anything like this

[Josh Woodward @joshwoodward]

Earlier today, we shipped our biggest update to Project Mariner yet! Here's a behind-the-scenes look at using it from @GoogleLabs.

With this version of Mariner,
1) You can oversee up to 10 simultaneous tasks
2) It has a feature called Teach and Repeat, where you can show it a task once, and it learns a plan for similar tasks in the future!

[Steven Johnson @stevenbjohnson]

Major update rolling out today at NotebookLM: a completely new adaptive design; interact with the Audio Overview hosts; and NotebookLM Plus--our premium version with expanded features.

Full features below 👇

New flexible "3-panel" interface lets you easily switch between asking questions, reading sources, and capturing your own ideas.

You can collaborate on writing tasks with a dual view of chat and notes, or ask followup questions via text while listening to an Audio Overview.

You can now “join” Audio Overviews with your voice and engage with the AI hosts to ask a question or steer the conversation. They'll adapt on the fly to (almost) everything you ask of them.

Expanded notes editor/viewer gives you more room to read and write

Auto-titled notebooks and notes

New NotebookLM Plus version, available through Google Workspace, Google Cloud, and (soon) Google One AI Premium. Plus features include:

300 sources per NotebookLM (up to 150 million words)—up from 50; raised limits for Audio Overviews, chat Q&A, and notebooks as well.

New sharing features optimized for using NotebookLM to create help centers or interactive guidebooks for your team or organization, with analytics to track usage

New "chat modes" that change NotebookLM's conversational style, including Guide (for help center/guidebook uses); Analyst (for strategic decision-making and planning); and a Custom setting that you can define.

[Corbin Cunningham, PhD @corbincito]

What an amazing journey it's been to get to play with and build this new experience @labsdotgoogle @joshtwoodward

[Josh Woodward @joshwoodward]

Project Mariner: Behind the scenes

What a fun ride with @GoogleDeepMind and @googlechrome on this one! One of our @labsdotgoogle team members has been using 5 computers to build and test it for the past few weeks!

[Jeff Dean @JeffDean]

We've released an early version of Project Mariner to trusted testers.

Project Mariner is an early research prototype built with Gemini 2.0 that explores the future of human-agent interaction. As a research prototype, it’s able to understand and reason across information in your browser screen, including pixels and web elements like text, code, images and forms, and then uses that information via an experimental Chrome extension to complete tasks for you.

Watch the video below for a sense of what it can do ⬇️

https://t.co/Lcbrs932r2

[Addy Osmani @addyosmani]

"The future of AI is agentic. That includes browsers!"

Imagine having an AI agent in your browser that can help you complete complex tasks, answer your questions, and streamline your workflow.

Today I'm thrilled to share a sneak peek at Project Mariner, a cutting-edge research collaboration between @googlechrome and @GoogleDeepMind, exploring the future of agentic AI within the browser!

Building on the power of Gemini 2.0, Mariner envisions AI agents seamlessly guiding users through online tasks, streamlining workflows and enriching browsing experiences.

Imagine having an intelligent co-pilot in your browser, anticipating your needs and proactively offering assistance. We're in the early stages of experimentation, focusing on core functionalities like understanding user intent, automating actions, and providing personalized recommendations.

This prototype leverages Gemini's advanced natural language understanding and reasoning capabilities to interpret user requests, both typed and spoken. Mariner can then interact with web pages, retrieve information, and even perform actions like filling out forms or navigating to specific sites.

For example, a user could simply ask "Find me a job near me," and Mariner would understand the request, navigate to a relevant job search site, and tailor the search based on the user's location and preferences. This is just one example of how we're exploring Gemini 2.0's potential to unlock agentic experiences through a series of prototypes, including:

1. Agents with multimodal reasoning: Project Astra, our research prototype exploring the capabilities of a universal AI assistant, is enhanced by Gemini 2.0.

2. Agents that can help you accomplish complex tasks: Project Mariner itself focuses on the future of human-agent interaction within the browser.

3. Agents for developers: Jules is an experimental AI-powered coding agent that integrates directly into a GitHub workflow.

4. Agents applied across domains: We're exploring agents for navigating video games and even applying Gemini 2.0's spatial reasoning to robotics.

We believe that integrating AI agents directly into the browser has the potential to revolutionize how we interact with the web. Project Mariner aims to make browsing more intuitive, efficient, and personalized.

By understanding user context and proactively offering assistance, Mariner can simplify complex tasks, save users time, and empower them to achieve more online. This aligns perfectly with the vision of Gemini 2.0 to create more helpful and intuitive AI experiences.

We’re currently testing Mariner with a small group of trusted users to gather feedback and refine the user experience. We believe that this technology holds immense potential to transform the way we browse and interact with information online.

[Sundar Pichai @sundarpichai]

We are investing in the frontiers of agentic capabilities with a few early prototypes. Project Mariner is built with Gemini 2.0 and is able to understand and reason across information - pixels, text, code, images + forms - on your browser screen, and then uses that info to complete tasks for you.

When evaluated against the WebVoyager benchmark, it achieved a state-of-the-art result of 83.5% working as a single agent setup.

[Google DeepMind @GoogleDeepMind]

What could the future of human-agent interaction look like in your browser? 🌐

Project Mariner is a research prototype built with Gemini 2.0 that’s able to research information and carry out tasks directed by you through an experimental Chrome extension.

See it in action ��

[Google Labs @GoogleLabs]

Introducing Project Mariner: an agent that helps you accomplish complex tasks in your browser 💻✨It’s a research prototype built with Gemini 2.0. Learn more: https://t.co/zWHTUydifK

[TechCrunch @TechCrunch]

Google unveiled its first-ever AI agent that can take actions on the web.

Called Project Mariner, the Gemini-powered agent takes control of your Chrome browser, moves the cursor on your screen, clicks buttons, and fills out forms, allowing it to use and navigate websites much like a human would.

Read more: https://t.co/5G0CVOPypQ

[Corbin Cunningham, PhD @corbincito]

So proud to have worked on this with such a talented team! Excited to see it out in the world. Congrats team! #GoogleLabs

[Google Labs @GoogleLabs]

Introducing Project Mariner: an agent that helps you accomplish complex tasks in your browser 💻✨It’s a research prototype built with Gemini 2.0. Learn more: https://t.co/zWHTUydifK

[Josh Woodward @joshwoodward]

Get your first-ever Spotify Wrapped AI podcast, built with @notebooklm. What a ride: from idea to shipped in 54 days. Cheers @labsdotgoogle and @Spotify teams!

https://t.co/6r3hd3KLn5

[Google DeepMind @GoogleDeepMind]

Transforming content into engaging audio conversations is just one feature of @NotebookLM 🗣️

@Stevenbjohnson and @Raizamrtn from the @LabsDotGoogle team believe it could be transformative for learning, research, and creative exploration too.

Join host Professor @fryrsquared as she discusses this and more on the latest episode of Google DeepMind: The Podcast ↓

Timecodes:
00:00 Intro
03:05 Hannah’s PhD
04:23 Reactions to audio overviews
08:45 Origins of NotebookLM
10:42 Source grounding
14:05 A tool for writers
15:22 Journaling
17:31 Why podcasts?
19:29 Evolution of audio generation technology
20:25 Interestingness
25:52 Soon to come capabilities
27:40 Hallucinations
29:09 Humor
32:00 Criticisms of the tools
39:10 Privacy
40:55 Future modalities
42:52 Limits of AI content creation
42:33 Hannah’s reflections

[Andrej Karpathy @karpathy]

Deep Dive is now my favorite podcast. The more I listen the more I feel like I'm becoming friends with the hosts and I think this is the first time I've actually viscerally liked an AI. Two AIs! They are fun, engaging, thoughtful, open-minded, curious. ok i'll stop now.

[Shiv Malik @shivmalik]

Google's NotebookLM is astounding. It's truly magical. More perhaps than ChatGPT was when it came out.
My 10 year old daughter and I converted one of her school poems into a podcast. Here's the result. It's a really thorough, enjoyable conversation. Full of context. It broke down several themes, and that in itself will make it an amazing teaching tool. I just can't believe this is AI but judge for yourself.

[Pascal Bornet @pascal_bornet]

This is the most impressive and instantly useful #AI demo I’ve seen so far!

It is called Google's NotebookLM.

I uploaded my entire new book "IRREPLACEABLE" and it transformed it into a podcast, study guide, FAQ, timeline, and an accurate chatbot that references specific parts of the book to support its answers.

Don't just take my word for it—listen to the podcast it generated for my book. It’s unbelievable. Seriously, take a listen... And yes, it's a bit unsettling, too!

What do you think?

#artificialintellligence

[Sundar Pichai @sundarpichai]

Amazed by how people are using NotebookLM, from a best-selling author researching his next book to nonprofits drafting grant proposals. Today we’re upgrading NotebookLM with new features and expanding it to many more places around the world.

[Corbin Cunningham, PhD @corbincito]

And we thought COVID was bad https://t.co/GRxHN2btiN.

#pigdemic