@NanoBanana create an image of 37.4419,-122.1419 at sunset
GENERATIVE AI
-
Codex AI Model Shows Rapid Progress and Growth
By
–
Codex progress and growth are both extremely rapid
-
Using AI for automated lecture summaries and visual cheatsheets
By
–
my favorite life hack
— God of Prompt (@godofprompt) 22 novembre 2025
> find a lecture on youtube
> get transcript from https://t.co/K4whdPH8oC
> paste it into gemini with this prompt:
"Generate an image. Turn this transcript into a cheatsheet with key takeaways, and give final output as 9:16 image created by nano banana.… pic.twitter.com/ACP6Ly3TKNmy favorite life hack > find a lecture on youtube
> get transcript from http://
ytscribe.ai
> paste it into gemini with this prompt: "Generate an image. Turn this transcript into a cheatsheet with key takeaways, and give final output as 9:16 image created by nano banana. -

LLM Council Web App Dispatches Queries to Multiple Models
By
–
As a fun Saturday vibe code project and following up on this tweet earlier, I hacked up an **llm-council** web app. It looks exactly like ChatGPT except each user query is 1) dispatched to multiple models on your council using OpenRouter, e.g. currently: "openai/gpt-5.1",
-
Emirates deploys ChatGPT Enterprise in strategic collaboration
By
–
strategic collaboration with @emirates
, including enterprise-wide deployment of ChatGPT Enterprise: -
Recursive Vibe Coding with Gemini and Google AI Studio
By
–
my brain just broke.
— God of Prompt (@godofprompt) 22 novembre 2025
i used gemini 3 to vibe code google ai studio inside a google ai studio..
inside of which i created another google ai studio
fully functional btw https://t.co/TU89IY9ZAF pic.twitter.com/rexZs3yUUgmy brain just broke. i used gemini 3 to vibe code google ai studio inside a google ai studio.. inside of which i created another google ai studio fully functional btw
-

EGGROLL: Gradient-Free LLM Training Achieves 100x Throughput
By
–
Could evolution replace gradients for LLM training? Introducing EGGROLL, a new paper that makes gradient-free training actually practical 100x training throughput vs vanilla ES 100x memory reduction 91% inference speed
Pure integer training Trending #1 on alphaXiv -
Vibe coding a game using Google AI Studio
By
–
this is so meta 🤯
— God of Prompt (@godofprompt) 22 novembre 2025
vibe coding a game in google ai studio created inside.. google ai studio
it's officially over. https://t.co/oIpVhWXNrJ pic.twitter.com/mRdnj5mZ4nthis is so meta vibe coding a game in google ai studio created inside.. google ai studio it's officially over.
-
Comparing ChatGPT and Claude storytelling capabilities
By
–
i really didn't see chatgpt 5.1 become better than claude in storytelling. need to test it more.
