Dr. Ray Bell

@OfficialLoganK @LyalinDotCom @GoogleAIStudio PDF to song wen?

Introducing Lyria 3 Pro and Lyria 3 Clip, our full song and 30 second music models, available starting today in the Gemini API and our all new music experience in @GoogleAIStudio!!

@_davideast Can you add storybook integration please so we can use our web design system

|￣￣￣￣￣￣￣￣￣￣￣￣￣ | | Stitch !== Static | |＿＿＿＿＿＿＿＿＿＿＿＿＿| \ (•◡•) / \ / —— | | |_ |_

@CraigTaylorViz @Kpler Cool. Guess that’s a key part of the story

@RayBell_DTN @Kpler It’s the result of GNSS interference, it distorts the signal to produce false signals, that’s why it’s so glitchy and vessels appear to float over land….

Following this weekend’s events, I’ve been analysing vessel activity in the Strait of Hormuz at @Kpler. Raw AIS from 28 Feb shows clear GNSS spoofing - vessels drifting over land and pulsing around fixed points (normally far cleaner). #AIS #DataViz #Maritime #StraitOfHormuz

This stunt feels irresponsible to me. If we don't want regular people developing toxic relationships with their chatbots it really doesn't help for leading labs to start giving them "retirement interviews" and encouraging them to blog their "musings and reflections"

Here is Gemini CLI’s February 18th weekly update for v0.29.0 - 🙋Ask User Tool: The model can now interactively pause execution and ask you questions for clarification, preferences etc, through a new dialog. - 🎉Gemini CLI Extensions: - Conductor | Automated Reviews: Close the loop with a "verify" step for quality, security, and compliance reporting. Conductor now peer-reviews logic, ensuring strict adherence to your plan​.md and style guides. gemini extensions install https://github.​com/gemini-cli-extensions/conductor - Firebase Agent Skills: Empower Gemini CLI with Firebase Agent Skills for a more seamless, efficient, and integrated development experience. gemini extensions install https://github.​com/firebase/agent-skills - 🛡️ High-Quality, Long-Running Sessions: We’ve optimized how the CLI handles massive amounts of data from tool outputs to prevent your context window from being overwhelmed. This means your conversations can now go on significantly longer while maintaining high reasoning quality, allowing for seamless performance even after executing complex commands - 🔍Enhanced Discoverability: Press ? on an empty prompt to toggle a new shortcuts panel directly above the input box. - ⌨️Vim Editing Experience: Added support for W, B, and E motions and operators, making terminal navigation feel more like your favorite editor. - 🥼Experimental: We plan to start including this section periodically, these features are in experimental stages and will be taking shape over the coming weeks. Please give us lot of feedback ! - 🗺️ Plan Mode (Experimental): Introducing a safe, read-only mode for researching and designing complex changes. Plan Mode prevents file modifications while you map the codebase and validate assumptions, ensuring your implementation strategy is solid before you write a single line of code. github.com/google-gemini/… 🧵

Because you wouldn’t let it slide… these are rolling out today for our most requested feature: Prompt-Based Revisions: Tweak, tailor, and tune your slides just by prompting the revisions you want PPTX Support: You can now export your Slide Decks (Google Slides coming next!)

@simonw Gemini app to voice input and output to models e.g pro

What's the best model you can directly have a voice conversation with these days? I believe ChatGPT still switches to a 4o-class model for voice conversations, I'd be happy to be corrected on that

🧭 gogcli v0.10.0 shipped: Google in your terminal. (really, Google should make this, but here we are) big Docs/Slides upgrade (markdown updates + tables, tab-aware read/edit, markdown/template slide creation, image-deck ops), Drive upload --replace + convert/share-to-domain, Gmail label delete + watch excludes, Contacts birthdays/notes and more... github.com/steipete/gogcl…

@_philschmid I need to digest how this differs from native Gemini API

Guide: philschmid.de/interactions-m… Docs: #multimodal_function_results" target="_blank" rel="nofollow noopener">ai.google.dev/gemini-api/doc…

Multimodal function calling is now available in the Gemini Interactions API, build agents that can see and process images natively. 🖼️ Tools return actual images, not text descriptions 👁️ Gemini 3 natively processes returned images 🛠️ Function results support mixed text and image 🆕 Guide on how to build visual agents with Python

Turn the terminal into your command center 🧑‍💻 The Google Workspace extension let's you catch up on Docs, write emails, ping colleagues in chat, schedule calls in your calendar... all without leaving the terminal! See it all in action...📜📨💬📅

@samuelcolvin @github @NotionHQ Google doc with workspace mcp server?

I find myself wanting a way to share and collaborate on markdown documents. @github isn't quite right - committing is too heavy, no simultaneous editing, web UI for review and editing isn't easy enough. @NotionHQ isn't quite right - hard to write locally (e.g. claude to edit) and sync easily, editing experience is more annoying than pure markdown. What I want is hosted markdown collaboration that easily let's me edit a file locally, and commits to github with an AI generated commit message regularly. Anyone know of such a tool?

📣 Open call to agent builders: Let's read agent skills from `.agents/skills`, so people don't have to manage separate folders per agent. Today we pulled the trigger for Codex to read `.agents/skills`. Goal is to deprecate `.codex/skills`. Pls like/tag/RT for momentum.

@JackWoth98 Can the CLI show images will a download button?

Making videos from the terminal with a few prompts 🤯 Working on a "video reviewer" subagent that will critique the video and continuously provide feedback until the video is high quality and meets brand guidelines etc... will share. P.S. Agent Skills are so fun to use, highly recommend!

@_philschmid Upstream to github.com/gemini-cli-ext… ?

Working on something. Is already helpful for my work. Should i ship it?

Ever wondered where words come from? 🗺️ built this app on @GoogleAIStudio called 'Wanderword' to map the evolution of language through time and space. It uses Gemini to trace linguistic roots and D3.js to animate the geographic migration of words through history. …derword-141284551734.us-west1.run.app

Can we have a @GoogleColab mobile app please? Couldn’t even paste code from @GeminiApp

PSA: You can vibe code with Gemini 3 Flash and Gemini 3 Pro for free in Google AI Studio app.new

Introducing Kaggle Community Benchmarks🔥 - Build and share your benchmarks - A unified interface across models - Custom tool use, Python interpreter, and LLM as judges Whether you're generating pelicans riding a bike or exploring agentic capabilities, this is for you

@emollick .@joshwoodward @OfficialLoganK

Gemini is held back by lack of tools, a big gap compared to ChatGPT and Claude. Gemini 3 is a really good model, but it just isn't able to do things. For example, take a GDPval prompt that involves downloading from the web, PDFs & docs. ChatGPT wins here, Claude close, Gemini😬