Miguel Somohano

Physics | Data scientist

[Google Antigravity @antigravity]

We’re transforming Google Antigravity into a scientific workbench. The new Science Skills bundle allows researchers to run complex workflows like protein analysis in minutes using specialized Alpha* models and 30+ major scientific databases.

[Google @Google]

Introducing Gemini for Science — a collection of AI tools to help accelerate the scientific process. Gemini can already assist in solving complex problems, but our new @GoogleLabs prototypes can help streamline more daily scientific tasks, including:

📃 Staying on top of new papers
🧑‍💻 Transforming research goals into usable code
💡Generating new hypotheses

#GoogleIO

[Google @Google]

We’re introducing Universal Cart — a new hub for shopping on Google.

🛍️ It will work across merchants and across services.

🛒 You’ll be able to add things to your cart whether you're shopping on Search, the @GeminiApp, @YouTube or @Gmail.

🛠️ The moment you add a product to your cart, it goes to work for you in the background. It finds deals and price drops, gives you insights on price history and alerts you when something comes back in stock.

🧠 It runs on our Gemini models, so your cart gets even smarter as the models improve.

💡 It also applies intelligent reasoning to your cart to help anticipate your needs. For example, if you add something to your cart that’s incompatible with something you already have in there, your cart catches it and suggests an alternative.

💲 It can find you hidden savings. Since it's built on Google Wallet, your cart understands your payment method perks, loyalty information and merchant offers so you don’t miss out on deals or points.

#GoogleIO

[Google @Google]

🛍️ Universal Commerce Protocol (UCP) does for agentic commerce what HTTP did for the web — it gives agents and systems a common language.

It makes everything from product research to checkout to shipment tracking seamless.

Starting soon, we’re bringing UCP to even more verticals like hotels and local food delivery providers — plus more surfaces, including @YouTube.

#GoogleIO

[Google @Google]

We asked our agents to build a working operating system from scratch using @Antigravity 2.0 and Gemini 3.5 Flash.

It took:
⏱️ 12 hours
🤖 93 parallel sub-agents
🔄 15k+ model requests
🧠 2.6B tokens processed
💸 Less than $1K in API credits

To build a functioning OS from scratch.

#GoogleIO

[Google @Google]

Gemini Omni Flash is rolling out starting today.

Here’s where you can find it:

🔹 Today: Google AI Plus, Pro and Ultra subscribers globally in the @GeminiApp and @FlowbyGoogle .

🔹Rolling out starting this week, for no cost: @YouTube Shorts and the YouTube Create app.

🔹Coming weeks: developers and enterprise customers via APIs.

#GoogleIO

[Google @Google]

Introducing Gemini Spark ✨

It’s your 24/7 personal AI agent that helps you navigate your digital life, taking action on your behalf, and under your direction.

🧠 It runs on Gemini 3.5 and is built on @Antigravity, so it can perform long-running tasks easily in the background.

⏱️ And because it runs on dedicated virtual machines on Google Cloud, you don’t even need to keep your laptop open.

🧰 Spark will integrate seamlessly with Google tools, and soon with third parties through MCP.

#GoogleIO

[Google @Google]

Meet Gemini 3.5 Flash — our strongest agentic and coding model yet.

It delivers frontier-level performance at 4x the speed of comparable frontier models — often at less than half the cost.

Generally available, starting today. 🧵

#GoogleIO

[Google @Google]

We’re expanding Google @Antigravity’s agentic surfaces and features — and they’re all available now for you to try.

🔹 Antigravity CLI
🔹 Antigravity SDK
🔹 Native voice support with Gemini Audio models
🔹 @Antigravity 2.0 desktop application
🔹 Integrations with @GoogleAIStudio, @Android, @Firebase, and the web

#GoogleIO

[Ronin @DeRonin_]

Andrej Karpathy: "90% of your AI coding bill is paying for context you didn't need to send"

Here are 10 things senior AI engineers stopped wasting tokens on:

1. Auto-context loading 50 files for a 30-line fix: $1.20/turn for tokens you'll never read. 80% input waste, every session

2. Running Opus on lint, format, and rename tasks: $0.60 for what Haiku nails at $0.02. 30x overpay on the cleanup tier

3. Tool call loops that re-send the full repo on every retry: 5x context cost per agentic flow. fixing these alone cuts 30-50% of bills

4. Sonnet as the default model: Kimi 2.6 matches its quality on most coding tasks at 1/6 the cost. defaulting to Sonnet in 2026 is leaving 60-70% on the table

5. Streaming responses on stable-prefix workflows: kills your prompt cache. you pay 10x for tokens that should have cost cents

6. "Just in case" file includes: 80,000-token prompts that should be 3,000. context bloat is the silent budget killer

7. Per-session knowledge rebuilding: 10 min writing a SKILL.md once vs paying agents to re-figure out your environment every run. $4 vs $0.30 per execution

8. Single-model setups: premium tier on every task is the most expensive mistake in AI coding right now

9. Asking 10 small questions one at a time: 10 separate input prefix charges vs one batched call. 70-90% savings on routine workflows

10. Buying Claude Pro + ChatGPT Plus + Cursor Pro: you seriously use one. the other two are habit, not utility

what actually compounds instead:

- context discipline (grep before fetching, always)
- prompt caching on every stable prefix
- multi-model routing (Kimi 2.6 default, Opus for the 10%)
- graduated skills via SKILL.md files
- profiling tool calls before optimizing prompts
- the routing mindset (right model for right task)

in 12 months, the gap between developers shipping on $200/month and $4,000/month budgets won't be skill

it'll be how well they route

study this.

[Google Cloud Tech @GoogleCloudTech]

Gemini CLI hooks best practice: use specific matchers.

Instead of running a hook for every tool, use the matcher property (e.g., "𝚖𝚊𝚝𝚌𝚑𝚎𝚛": "𝚠𝚛𝚒𝚝𝚎_𝚏𝚒𝚕𝚎|𝚛𝚎𝚙𝚕𝚊𝚌𝚎") to limit execution to relevant events.

More tips ↓ https://t.co/gp1YkF7MBS

[Google Gemini @GeminiApp]

Gemini can now transform your questions and complex concepts into customizable interactive visualizations directly in your chat.

Adjust variables, rotate 3D models, and explore data for a more immersive way to learn and explore in Gemini.

[Google Gemma @googlegemma]

Gemma 4 can run on phones without an internet connection! 🤯

It can perform local agentic tasks, such as logging and analyzing trends. When connected, it can also make API calls.

Want to try it yourself? Get the Google AI Edge App on iOS or Android. (🔊 Sound on for the demo!)

[Stitch by Google @stitchbygoogle]

Meet the new Stitch, your vibe design partner.

Here are 5 major upgrades to help you create, iterate and collaborate:
🎨 AI-Native Canvas
🧠 Smarter Design Agent
🎙️ Voice
⚡️ Instant Prototypes
📐 Design Systems and DESIGN.md

Rolling out now. Details and product walkthrough video in 🧵

[Google Maps @googlemaps]

Google Maps 🤝 Gemini 3

Now that you can ask Maps complex questions, let’s dig into some prompts that showcase the true power of this update. 🧵

[Gemini CLI @geminicli]

Ask User tool in Gemini CLI 💬

The ask user tool gives the agent an interface to ask questions to you when instructions are unclear, designs could go one of multiple ways, or when you ask it to use the "ask_user" tool!

Supports multiple different question types.

Give it a try today to review your specs, quiz you, or just ask you questions about a project. 🙋

[Google AI @GoogleAI]

We’re introducing a series of updates that make Gemini in @googlechrome more helpful, efficient, and personalized for you:

— Side panel for multitasking: The new side panel experience allows you to do things like send emails or compare information without leaving your open tab

— Nano Banana integration: Generate and edit high-fidelity images right from the new side panel

— Deep ecosystem integration: Connect Google apps like @gmail, @googlecalendar, @YouTube, Google Shopping, and Google Flights to accelerate complex task execution

— Personal Intelligence: With your permission, Personal Intelligence turns Chrome into a trusted partner that remembers past conversations and connects with your Google apps to provide help that’s uniquely tailored to you

— Agentic action via auto browse: Offload multi-step browser tasks, like scheduling an appointment or filling out a complex form, using our new auto browse feature that’s rolling out in preview for U.S. Google AI Pro and Ultra subscribers

— Support for agents: Support for Google’s Universal Commerce Protocol (UCP) ensures AI agents can execute transactions on your behalf

— Enhanced security: New rigorous security standards designed to protect against emerging kinds of online threats

The new Gemini in Chrome is available on Windows, macOS, and Chromebook Plus in the U.S. We’re just beginning to explore the possibilities of an agentic web, so stay tuned for more news here.

[Swapna Kumar Panda @swapnakpanda]

Stanford’s FREE Machine Learning Courses:

CS221 - Artificial Intelligence
CS229 - Machine Learning
CS230 - Deep Learning
CS234 - Reinforcement Learning
CS224N - NLP with Deep Learning

Find course links inside:

[Analysis Fact @AnalysisFact]

The Tensor Cookbook

https://t.co/Yvuh4IMg1e

[Charlie @Carlodmension]

La generación que prefirió endeudarse con viajes y no con apartamentos.