Paige Bailey
@dynamicwebpaige.bsky.social
9.2K followers 55 following 230 posts
✨ Keep it simple, make it scale. AI should be about empowering users and building understanding. 👩‍💻 AI Developer Experience @ Google DeepMind, ex-Github, ex-Google
Posts Media Videos Starter Packs
Pinned
dynamicwebpaige.bsky.social
👋 Greetings + welcome, new BlueSky-gazers!

I'm an engineer working on the developer experience for @Google's AI tools, especially aistudio.google.com, its API keys, @GoogleColab, Gemma open-source models, @Kaggle, and JAX.

I post use cases, quick technical overviews, and images of hiking trips. 😀
Google AI Studio
Google AI Studio is the fastest way to start building with Gemini, our next generation family of multimodal generative AI models.
aistudio.google.com
dynamicwebpaige.bsky.social
wild what you can do with Veo 3 and Gemini 2.5 Flash Image Preview in Google AI Studio - testing out here with a public domain song, a picture of me, and music styles decade by decade
dynamicwebpaige.bsky.social
👋 Want to make sure that your favorite IDEs and extensions (Roo Code, Cursor, Windsurf, etc.) always use the latest Gemini API models and features?

Make sure to either add one of the files below into your context window, or MCP-ify the SDK repo:

🔗 JS/TS: lnkd.in/g8nn7GVT
🔗 Python: lnkd.in/g4XKNF-j
dynamicwebpaige.bsky.social
🖌️🧵 Convert any painting (or photo!) into a paint-by-numbers template, or a counted cross-stitch pattern:
dynamicwebpaige.bsky.social
🍌 There's always money in the banana stand!

Make sure to check out our latest model in Google AI Studio - Gemini 2.5 Flash Image Preview. Editing, reimagining, extraction and more.

🖼️: "The Green Cap" by Alex Katz
dynamicwebpaige.bsky.social
a poem about
ai art

assembled by an
ai

which composed
news headlines about
ai art

gist.github.com/dynamicwebpa...
dynamicwebpaige.bsky.social
small-batch, artisanal, performance-enhancing beverage handcrafted from the purest COCO dataset, with subtle flavor grad-ients 🥥😂
dynamicwebpaige.bsky.social
📸 Imagen 4 Ultra in Google AI Studio is extremely, *extremely* good at generating images that look and feel like they were taken with a Polaroid camera.

Test it out yourself: aistudio.google.com
dynamicwebpaige.bsky.social
🔗https://github.com/langchain-ai/multi-modal-researcher?tab=readme-ov-file
dynamicwebpaige.bsky.social
📽️ Simple research and podcast generation workflow using LangGraph and Gemini 2.5!

You can pass a research topic and a YouTube video; the system will then perform research on the topic using search, analyze the video, combine insights, and generate a report with citations as well as a short podcast.
dynamicwebpaige.bsky.social
Google AI Studio + @github.com = 🚀!

You can now link the apps that you create with your GitHub (personal or private repos). Happy building!
dynamicwebpaige.bsky.social
Reminder: DeepMind's Gemma 3n model is performing about as well as Gemini 1.5 Pro – better, in many cases! – and is only 4B parameters in size.

The best model 6 months ago is now small enough to be run on a laptop. Now play that forward 6 months from now, thinking about the best models of today. 🤯
dynamicwebpaige.bsky.social
Get ready to enter the simulation...

Genie 3 is a new frontier for world models: its environments remain largely consistent for several minutes, with visual memory extending as far back as 1min. These limitations will only decrease with time.

Welcome to the future.🙌
deepmind.google/discover/blo...
dynamicwebpaige.bsky.social
📝 Tired of having too many tabs open, but no time to read through all of them?

Just built a Chrome extension using AI Studio's URL Context feature - all you have to do is add an API key, and the extension uses Gemini 2.5 Flash Lite to summarize all of your open tabs.

🔗 github.com/dynamicwebpa...
dynamicwebpaige.bsky.social
🚀 The Gemini APIs in Google AI Studio can be used to understand – and also to generate! – many different output modalities:

Video, images, audio, text, code, or all of the above all at once.

If you've only been using the models to generate text and code, you're missing out. 👇

ai.google.dev
dynamicwebpaige.bsky.social
🏗️ More problem sets like this one from @mitocw.bsky.social, please:

"The intent of this first civil engineering design project is to let you get a feeling for [material properties and constraints] -- by going from playing to building and assessing *what* you do and *why*."
dynamicwebpaige.bsky.social
Standing room only for the @majorleaguehacking.bsky.social + Google DeepMind + Google Cloud AI Roadshow in San Francisco!

"This is the single greatest moment in history to become a software engineer, or a technologist – to be anyone who is creating digital artifacts. And we're only just beginning."
dynamicwebpaige.bsky.social
🗺️ New favorite use case for Google AI Studio's Build:

1️⃣ Use Gemini w/Search Grounding to identify specific places (ex: dog-friendly parks in SF; pickleball courts that are bookable on weekends; aestheticians that use Dermalogica products; etc.)

2️⃣ Then use @openstreetmap.bsky.social to visualize.
dynamicwebpaige.bsky.social
somehow I missed that there is a Foundation TV series (!!) and that Lee Pace is in it (!!!), bonus points with the shirtlessness

this is going to be a long night
a man in a blue suit stands next to a woman in a dark room
ALT: a man in a blue suit stands next to a woman in a dark room
media.tenor.com
dynamicwebpaige.bsky.social
[...] 15 year archive totaling more than 116M tokens in a single batch. It took just one command and just 39 minutes to process the complete archive, yielding 154,739 distinct stories: an average of 10.5 stories per broadcast.

Most incredibly of all: it cost just $153.80 to do all of this!"
dynamicwebpaige.bsky.social
We used the standard off-the-shelf public Gemini 2.5 Flash Thinking model without any modifications. No data was used to train, tune or otherwise contribute to any model: we used Gemini only to create an index of each broadcast.

We make use of Gemini's batch processing to analyze the entire [...]
Building A Story Index Of A Decade Of TV Evening News With Geocoding, Sentiment, Frame & Narrative Analysis In 1 Hour For $154 – The GDELT Project
blog.gdeltproject.org
dynamicwebpaige.bsky.social
"In collaboration with the @archive.org TV News Archive we examined 14,749 evening news broadcasts spanning the big three networks from July 2010 to present, asking Gemini 2.5 Flash Thinking to make an index of the stories covered in each broadcast, geography, sentiment, frame, narrative structure.
dynamicwebpaige.bsky.social
🥳 The @majorleaguehacking.bsky.social + Google DeepMind AI Roadshow is happening tomorrow in SF!

Six hours of learning and experimenting with the latest Gemini and Veo models in Google AI Studio, seeing what others have built, great food and drinks, and even better company.

🔗 lu.ma/SFroadshowML...
dynamicwebpaige.bsky.social
Just finished presenting on the Gemini APIs, Google AI Studio, Gemma 3 and 3n, @googlecolab.bsky.social's Data Science Agent, and @googlelabs.bsky.social's Jules to a group of educators and engineers at Stanford.

Thanks for having @developers.google.com and Google Cloud come visit today! 🌲 ☁️