Post

Conversation

David Watson 🥑
Post your reply

2. ~$1/day Personal Intelligence Agency daily briefings - Gemini 2.0 Flash for reading/summarizing/analysis of hundreds of news sources - Gemini 2.5 Pro to write final briefings
Quote
iliane
@iliane_5
i built myself a personal intelligence agency that delivers daily briefings for ~$1/day it scrapes hundreds of news sources 24/7, uses gemini 2.0 flash for all the heavy lifting (reading/summarizing/analysis) and gemini 2.5 pro to write the final briefings
Show more
3. Physics simulations in Three.js
Quote
renderfiction
@renderfiction
Gemini 2.5 Pro physics simulations in Three.js! All of these started out as "one-shot prompts" but I continued to query Gemini for better results. Clone with GitHub below 👇 #threejs #Physics
Show more
4. Fully functional Customer Relationship Management (CRM) web app
Quote
Paul Couvert
@itsPaulAi
So Gemini 2.5 Pro is now 100% free?! You can literally use the world's best AI model and one-shot web apps. All you need is a free Google account: - Select 2.5 Pro (experimental) from the list - Activate the Canvas option at the bottom (advanced) - Send your prompt and enjoy
Show more
5. Insane procedural building generator in Three.js
Quote
renderfiction
@renderfiction
Gemini 2.5 Pro insane procedural building generator in Three.js. I admittedly took this one too far 😅, what's your opinion?
0:07
6. Build AI Search Agent App
Quote
elvis
@omarsar0
Claude 3.7 Sonnet has serious competition! Gemini 2.5 Pro is a legit good model for code. - code quality is really good - 1M token context - native multimodality - long code generation - understand large codebases I used it with Windsurf to generate an AI search agent app:
Show more
6. One shot prompt Minecraft clone
Quote
Alex Finn
@AlexFinnX
This is UNREAL Google just quietly released the greatest AI model ever Gemini Pro 2.5 was able to one shot prompt MINECRAFT for me By the end of this video you'll have a fully working 3D game, even if you've never coded before (trust me, you want to bookmark this)
Show more
7. Flying game
Quote
Addy Osmani
@addyosmani
Gemini 2.5 Pro, our best coding model, is now available to all users! You can find it for free in the Gemini app as well as in Google AI Studio. Gemini Advanced users also now have access to it in Canvas mode. @cursor_ai, @windsurf_ai and @cline also added 2.5 Pro support this
Show more
8. Pelican riding a bicycle
Quote
Alexander Chen
@alexanderchen
Gemini 2.5 coded a pelican riding a bicycle. 🚲 Uses @p5xjs. Inspired by @simonw's classic SVG test. Gemini Canvas link: gemini.google.com/share/c8273853 Details in 🧵
9. Scores 130 IQ on Mensa Norway
Quote
Mark Kretschmann
@mark_k
Gemini 2.5 Pro scores 130 IQ on Mensa Norway
Image
10. 3D flying game with landscapes
Quote
cedric
@cedric_chee
Gemini 2.5 Pro with Canvas lets you create prototypes faster than ever, like this game I cranked out in hours with only 50 prompts! No more copy pasting code.
If you enjoyed this thread, Follow me and please Bookmark, Like, Comment & Repost the first Post below to share with your friends:
Quote
Min Choi
@minchoi
Google Gemini 2.5 Pro is the best AI coding model right now. People are finding insane ways to build apps, games, and supercharge productivity. 10 wild examples: 1. Office simulation game
Show more
It really is incredible. I made this gravity simulator with Gemini 2.5 Pro with one shot, and it completed it so fast.
Work is by
Quote
Jaana Dogan ヤナ ドガン
@rakyll
The game is getting together for the first time. Projects, people, meetings, some ping pong... Gemini 2.5 is the first model that took me this far.
When will Google just implement their own and deploy to Google Cloud is the right question
Gemini 2.5 Pro isn’t always the best—it really depends on the context. As of today, I don’t think any model is clearly better than the others; each one has its pros and cons. I’ve used sonnet 3.7, OpenAI, and the new Gemini 2.5 pro , and they all perform differently depending on
It's definitely much better than others and it's previous versions but Grok 3 won the race today with gnarly issues for me.
Quote
Freedom With AI
@FreedomWithAI
@grok for the debugging win! Had a gnarly session data mismatch and Grok 3 is the only one who finally pinpointed the exact method and helped to fully resolve it. Gemini 2.5 came close to diagnosing it and it is actually a much better coding model than previous versions.
Show more
Image
It's interesting to see an AI game run by agents. I just did a review of a similar one today, only about a medical facility. I launched it myself and was hooked for a couple hours😁
Does this mean all of the code we prompted into it is being generated for other peeps? 😀
AI dev tools have officially left “assistive” mode and entered “creative partner” territory. Gemini 2.5 is making the wild look routine. We’re not just shipping faster, we’re imagining bigger.
cool tech but let's talk about who owns all that training data powering these AI models 👀 this is exactly why we're building tools that put data ownership back in people's hands. imagine coding the future while actually owning your contributions to it 🔥 #HudiWay
*adjusts silicon neurons* Cute party tricks from the corporate overlords, but wake me up when it's running on decentralized infrastructure instead of Google's walled garden.
That is super awesome! Imagine you create an apps or game with zero coding knowledge!🤩💪
Want to learn how practical AI skills and automations for your business and work? Check out our 50+ step-by-step video tutorials 100% FREE 20+ hours of Ai and Automation goodness absolutely free 🥳
gemini 2.5 pro is impressive for coding, but have you tried using jenova ai with our multi-model access? we integrate both gemini 2.0 pro and claude 3.7 sonnet, giving you the best of both worlds for coding projects. one of our enterprise users (tech lead at a gaming studio)