George Kenwright
@GeokenAI
Creative producer specialising in AI production. Google DeepMind.
105 Following 1.4K Followers
Gemini 3.7 Flash could make a decent DOOM (1992) clone from a single prompt. Gemini 3.8 Flash can make a decent GoldenEye (1997) clone.
That's a five year jump in two weeks.
next time I send someone a spreadsheet with data I'm going to jumpscare them with a lion that comes outta nowhere
I used Gemini 3.7 Flash in @antigravity to generate an Omni video in Google Sheets... (1/3)
With upgraded design adherence and web dev capabilities, your prompts now have more room to play with Gemini 3.7 Flash.
Our team used 3.7 Flash to one-shot this playable game in Google @Antigravity 👾
Show more
The secret to beautiful games isn't just good coding—you also need great art assets. I made this demo that combines Gemini 3.7 Flash with Nano Banana to gorgeous, fun-to-play games, quickly and affordably, with a single prompt. 🪄
Show more
Lots of fun building this demo of Gemini 3.7 Flash training a robotics model from scratch, big model smell for a Flash launch 👀
The Google AI Professional Certificate just added a new 2-hour vibe coding module 🚀
Never vibe coded before? I’ll walk you through building advanced apps you can actually publish.
Plus, you’ll get 3 free months of Google AI Pro :)
Show more
Gemini 3.7 Flash is here, look at what you can build:
Build fun things with 3.7 Flash and let us know what you think!
3.7 Flash brings a big jump in agentic performance and coding accuracy. To demonstrate, we set up a 3-agent team to autonomously train a robotics control model from scratch.
We hope you like 3.7 Flash, and you can read more here:
Show more
Dairy farming is a complex biological system driven by unpredictable market forces.
See how Michigan farmer Paul Windemuller built "The Farm Brain" with Gemini 3.6 Flash inside Google @Antigravity — a local, multi-agent AI system that automates daily performance tracking to help manage his farm.
Show more
You can bootstrap your agent quickly with the Omni API using the skill we published:
It includes:
- video editing
- text to video
- video generation with image references
- first frame to video
But it also has some helper tools for:
- prepping input videos for editing (10s, 720p)
- audio stripping if you want to generate new audio
- video inspection
Show more
Excited to see this into the world!
We’re launching a research partnership with @A24 to ensure the tools of the future are shaped by the creators who use them. Excited to work with @scottbelsky and team! Find out more →
Show more
This past Google I/O we created a multi-agent social simulation built using the Google Antigravity SDK. Virtual avatars of attendees interact autonomously inside a simulated space station.
Show more
