I think it helps people make their prompts more complex. I don't think the actual JSON bit is necessary.
PROMPT ENGINEERING
-
AI models struggle with sensitive topics and prompt limitations
By
–
Y no es sólo con ese prompt concreto, sino con según que temas delicados le preguntes.
-
Grok 4 Relies on Web Search Results and Online Code
By
–
Grok 4, in general, is very influenced by search results and pretty credulous when it sees a web search result. When you ask it to code, it often looks for code online first and uses that.
-
Grok 4 Generates Crowd Animation Spelling Hello World First Try
By
–
Grok 4 a codé ça du premier coup 😅 Nous allons commencer à voir des test de plus en plus fou
— VISION IA (@vision_ia) 11 juillet 2025
Traduction du tweet original :
C’est incroyablement bon !
J’ai demandé : « Crée une animation d’une foule de personnes marchant pour former les mots “Hello world, I am Grok” pendant… https://t.co/27I9UT7so5 pic.twitter.com/vr9D1ueDA5Grok 4 a codé ça du premier coup Nous allons commencer à voir des test de plus en plus fou Traduction du tweet original : C’est incroyablement bon ! J’ai demandé : « Crée une animation d’une foule de personnes marchant pour former les mots “Hello world, I am Grok” pendant
-
Good AI Model with Unusual Prompting Techniques
By
–
He’s a good one!
(with some of the weirdest prompting) -
Experts unlock AI productivity gains through dedicated effort and learning
By
–
Users, especially experts, are often quite capable of figuring out ways to use AI systems for significant productivity and performance gains, but it does take some time and effort.
-
AI Agent Effectiveness Depends on User Skills and System Integration
By
–
Unless and until agents really do work at expert level, the benefits of AI use are going to be contingent on the skills of the AI user, the jagged abilities of the AI you use, the process into which you integrate use, the experience you have with the AI system & the task itself
-
Grok 4 Heavy solves prompt regular Grok 4 fails, takes 26m 45s
By
–
Grok 4 update: Regular Grok 4 doesn't appear to be able to solve the prompt at the top of this thread (0/7 attempts) but Grok 4 Heavy got it on the first try—though it took >4x longer than o3-pro, returning in 26m 45s:
-
Pronoun Omission Changes AI Model Behavior Patterns
By
–
Interestingly, not saying "you" changes this behavior!