Nano banana pour la première Frame, ensuite JSON prompting avec ChatPPT et veo 3 pour la vidéo
PROMPT ENGINEERING
-
Turning Prompt Engineering into a Skill
By
–
This method turns prompt engineering into a repeatable professional skill set.
-
AI Model Achieves 90% Accuracy on Prompt Tasks
By
–
I have tried both. This one just makes the flow from a prompt and get things right 90% of the time.
-
Self-Rewarding Vision-Language Model Through Reasoning Decomposition
By
–
Self-Rewarding Vision-Language Model via Reasoning Decomposition
-
Prompt to Simulate a Product Launch
By
–
Steal my Claude Opus 4.1 prompt to create a simulated environment and test your product launch or post performance before going public. ————————————-
EXPERT SIMULATION ARCHITECT
————————————- Assume the role of an expert in reality simulation. -
Detailed Prompts Performance Comparison Between AI Models
By
–
It is as good as sonnet if not better. But for detailed prompts I found it better in many cases.
-
Pro Tip: Combining GPT-4, Flux, and Gemini Flash for Images
By
–
Astuce de pro – GPT-4 ou Flux pour la génération d’images
– Gemini Flash (Nano Banana) pour les retouches La combinaison fonctionne vraiment bien. -
Agentic Knowledge Graph Construction for Enhanced RAG Systems
By
–
Build better RAG by letting a team of agents extract and connect your reference materials into a knowledge graph. Our new short course, “Agentic Knowledge Graph Construction,” taught by @Neo4j Innovation Lead @akollegger, shows you how.
— Andrew Ng (@AndrewYNg) 27 août 2025
Knowledge graphs are an important way to… pic.twitter.com/wBk7ok5uWvBuild better RAG by letting a team of agents extract and connect your reference materials into a knowledge graph. Our new short course, “Agentic Knowledge Graph Construction,” taught by @Neo4j Innovation Lead @akollegger
, shows you how. Knowledge graphs are an important way to -
Prompt Engineering Goodbye Context Engineering Welcome
By
–
He publicado un episodio en @ivoox
: "La ingeniería de prompts en IA dice ADIÓS. ¡Viva la ingeniería de contexto! #podcast -
LLM Evaluations: Highest ROI Strategy for Model Optimization
By
–
If you’re not measuring, you’re guessing. Here’s why LLM evaluations are the highest-ROI move 👇
— Louis-François Bouchard 🎥🤖 (@Whats_AI) 27 août 2025
– Most failures come from bad specs, no real data, or models misapplying rules
– Fix it with custom evaluations: JSON checks, tool errors, schema constraints, LLM-as-judge
– Build… pic.twitter.com/JtEtklqM4PIf you’re not measuring, you’re guessing. Here’s why LLM evaluations are the highest-ROI move – Most failures come from bad specs, no real data, or models misapplying rules – Fix it with custom evaluations: JSON checks, tool errors, schema constraints, LLM-as-judge – Build