we're testing relax mode on the pro tiers and higher right now. try auto prompting at first then just try exploring writing more detailed motion prompts
PROMPT ENGINEERING
-
Meta Launches Llama 4 with Mixture-of-Experts Architecture
By
–
Introducing "Building with Llama 4." This short course is created with @Meta @AIatMeta, and taught by @asangani7, Director of Partner Engineering for Meta’s AI team.
— Andrew Ng (@AndrewYNg) 18 juin 2025
Meta’s new Llama 4 has added three new models and introduced the Mixture-of-Experts (MoE) architecture to its… pic.twitter.com/HxCND1Fs1TIntroducing "Building with Llama 4." This short course is created with @Meta @AIatMeta
, and taught by @asangani7
, Director of Partner Engineering for Meta’s AI team. Meta’s new Llama 4 has added three new models and introduced the Mixture-of-Experts (MoE) architecture to its -
How to Start Creating AI Agents Podcast Episode
By
–
He publicado un episodio en @ivoox
: "Cómo Empezar a Crear Agentes de IA #podcast -
Automated Prompt Engineering: No-Code MVP
By
–
Prompt engineering with automation is a deadly combo. You can go from idea to MVP without touching a single line of code. Zero barrier.
-
SheetAI: AI-Powered Spreadsheet Automation for Google Sheets
By
–
2. SheetAI Say what you need — SheetAI translates it into spreadsheet logic. With a Google Sheets add-on, you can write prompts like “Show top-selling items this quarter,” and it generates functions for you.
-
Explore random style space corners with –sref prompt parameter
By
–
Wow these are quite nice! Try using –sref random at the end of your prompt to explore random corners of "style space". The word "random" will get replaced with a number (as below) which you can repeatably use for consistency or share with others around the globe.
-
Trust Models More for Successful Agentic Orchestration
By
–
You should trust the model more than you think. It’s the only way to build a successful agentic orchestration. Don’t worry about what the model can’t do. Build for the impossible.
-
AI respects anatomical accuracy despite conflicting prompt constraints
By
–
Me gusta el detalle de que la IA ha respetado la localización del ojo del pangolín a pesar de que por la ubicación de las gafas –que le he pedido yo en el prompt– tendrían que estar en otra posición.
-
MCP Crash Course Video Tutorial Explained
By
–
🤔 If you've heard of MCP but don't really know what it is, we got you. Check out this short crash-course video from @zeke:https://t.co/tTUOwWNjPe
— Replicate (@replicate) 17 juin 2025If you've heard of MCP but don't really know what it is, we got you. Check out this short crash-course video from @zeke
: -
o3 and o3-pro inconsistent; only amusing results posted
By
–
No, but I’m only posting the interesting / amusing ones. o3 is hit-or-miss on this prompt (as is o3-pro) particularly the part of it being a sensible answer to the question.