Mistral released Mistral Small 3.2-24B, a minor update for the Small-3.1 model, with: —Enhanced instruction following capabilities
—More robust function calling
—Fewer infinite generations or repetitive answers
PROMPT ENGINEERING
-
Mistral Small 3.2-24B: Enhanced Instructions and Function Calling
By
–
-
LLM Completion Prompts Sentient AGI Poetry Without Formal Correctness
By
–
I don’t think that this is a text about the experiences of LLMs, but the completion of a prompt that effectively amounts to “the following is a text about a sentient AGI model talking poetically about experiencing itself (but without ambitions for formal correctness)”?
-
Keep Your Authentic Voice While Using AI Tools
By
–
ChatGPT is turning everyone into a Shakespeare.
But the world doesn’t need more Shakespeares. It needs people like you and me.
The ones who say “ugh” instead of “alas,”
Who’d rather use a GIF instead of words from the thesaurus. Use AI. But keep it “you”. -
Experts Evaluated on Prompt Compliance, Not Accuracy
By
–
Experts are not getting punished for mismodeling and mismanaging reality, but for completing the prompt in the wrong way. Experts have to train every day, on the opinion pages of the highest status news, science journals and social media
-
Midjourney Video Sound Tip: Use Elevenlabs for Custom Sound Effects
By
–
Pro tip for sound if you're messing around with Midjourney Video:
— AI Breakfast (@AiBreakfast) 23 juin 2025
You can use Elevenlabs to generate any sound effect via prompting. Each one ends up being pennies. Most of these sounds fx were one-shot
Way more fun than leaving sound to the video generator imo (like in Veo 3) pic.twitter.com/7oVRuzyOsBPro tip for sound if you're messing around with Midjourney Video: You can use Elevenlabs to generate any sound effect via prompting. Each one ends up being pennies. Most of these sounds fx were one-shot Way more fun than leaving sound to the video generator imo (like in Veo 3)
-
Expert AI Knowledge Prompt Completion Over Base Reality
By
–
an expert is someone who knows that correctly completing the prompt is more important than base reality
-
Implementing Conversational Memory in LLMs with LangGraph
By
–
Memory in LLMs A practical guide showing how to implement conversational memory in LLMs using LangGraph, demonstrated through a therapy chatbot. Features code examples for basic retention, trimming, and summarization approaches. Learn to build memory-aware apps
-
Recommendation to use Claude 4 Sonnet
By
–
For Claude, I suggest you use Claude 4 Sonnet. Opus is not made for this type of tasks. pic.twitter.com/8JmWkfVtTC
— God of Prompt (@godofprompt) 22 juin 2025For Claude, I suggest you use Claude 4 Sonnet. Opus is not made for this type of tasks.
-
Advice on Which ChatGPT Model to Use
By
–
To get best results from ChatGPT… use o3 model or 4o. pic.twitter.com/WUvjaDMh2w
— God of Prompt (@godofprompt) 22 juin 2025To get best results from ChatGPT… use o3 model or 4o.
-
AI-generated custom learning curricula
By
–
The next generation of learners won’t be course buyers. They’ll be course generators. This is how you start: Paste the prompt.
Share your goal + time.
Get your custom curriculum.
Start learning instantly. No logins. No paywalls. Just progress.