This is a prompt engineering challenge, not a vibe coding one imo.
PROMPT ENGINEERING
-
Google Releases 68-Page Document Redefining Prompt Engineering
By
–
Google a publié un doc de 68 pages qui redéfinit la manière de parler aux IA.
— VISION IA (@vision_ia) 21 avril 2025
Oubliez les hacks TikTok : c’est peut etre la prochaine Bible du prompt engineering.
Boîte à outils ultra-concrète, peu exploitée.
Si vous bossez avec l’IA, vous ne pouvez pas passer à côté.
👇 Je… pic.twitter.com/dVVXHUniADGoogle a publié un doc de 68 pages qui redéfinit la manière de parler aux IA. Oubliez les hacks TikTok : c’est peut etre la prochaine Bible du prompt engineering. Boîte à outils ultra-concrète, peu exploitée.
Si vous bossez avec l’IA, vous ne pouvez pas passer à côté. Je -
What screen-aware AI can do: summarize, recommend, guide, write, answer
By
–
What can it actually do?
— God of Prompt (@godofprompt) 21 avril 2025
• Summarize a full web page
• Recommend products from a list
• Walk you through recipes step-by-step
• Help write a cover letter for a job post
• Answer questions about any page's content
It’s like ChatGPT, but screen-aware. pic.twitter.com/BcvqnJ665hWhat can it actually do? • Summarize a full web page
• Recommend products from a list
• Walk you through recipes step-by-step
• Help write a cover letter for a job post
• Answer questions about any page's content It’s like ChatGPT, but screen-aware. -
Ultimate GPT Wrapper Blueprint for Wealth Creation
By
–
Steal my prompt to build GPT wrappers that turn complex tools into simple money-makers non-technical people will happily pay for. —————————————–
ULTIMATE GPT WRAPPER BLUEPRINT
—————————————– ## WEALTH CREATION THROUGH AI -
ReACT Guide: Building Reasoning Agents with Gemini
By
–
Gemini ReACT Guide Phil Schmid just released a guide showing how to build reasoning agents using Google's Gemini 2.5 and LangGraph, featuring examples for audio analysis, function calls, and structured data. Explore the guide!
Guide link in reply -
O3 vs O4 Mini: Coding Tetris Reveals Key Differences
By
–
J’ai demandé à chatgpt O3 et O4 Mini de coder un Tetris…
— VISION IA (@vision_ia) 20 avril 2025
Résultat : O3 m’a bluffé. Il anticipe, structure, ajoute des features non demandées (IA entraînable, reset, UX claire).
O4 Mini va plus vite, mais reste simpliste.
Extrait de ma dernière vidéo : pic.twitter.com/5X0MCdezmWJ’ai demandé à chatgpt O3 et O4 Mini de coder un Tetris… Résultat : O3 m’a bluffé. Il anticipe, structure, ajoute des features non demandées (IA entraînable, reset, UX claire). O4 Mini va plus vite, mais reste simpliste. Extrait de ma dernière vidéo :
-
Test AI prompts to find which model truly thinks like a human
By
–
Now copy and paste these prompts yourself and test out these models. See which one really thinks, feels, and reasons like a human and which one’s just good at pretending.
-
Goalpost Movement in AGI Debate: Returning to OpenAI’s Definition
By
–
I feel like the goalpost movement in my tl is in the reverse direction recently, with LLMs solving prompt puzzles and influencers hyperventilating about AGI. The original OpenAI definition is the one I’m sticking with, I’m not sure what people mean by the term anymore.
-
Reinforcement Learning State for LLM Reasoning Optimization
By
–
The State of Reinforcement Learning for LLM Reasoning
A must-read deep dive by Sebastian Raschka @rasbt
. Essential if you're into aligning, optimizing, or understanding how RL shapes reasoning in LLMs. -
OpenAI Adds Image Generation to Custom GPTs
By
–
OpenAI prepares Custom GPTs for native GPT-4o image generation. The setting seems to be already working, and you can try it on "Cyberpunk Artist" GPT. However, it doesn't follow GPT instructions in 50% of cases yet.