Jad Bourji

Prompt engineering has changed a lot recently. I remember around this time last year, strict prompt engineering rules were a must. From You are a professional persona setting, to zero-shot, few-shot CoT techniques, these were necessary for quality outputs

Nowadays, it feels as if AI models do the engineering all by themselves without user input. They understand us well even if we re just casually typing (some call it lazy prompting , and I even saw a product related to this on PH)

For those who haven't tried it yet it's a new feature in GPT-4o that lets the chatbot proactively message you at scheduled times. Just type something like "Remind me to check my email tomorrow at 10 am," and it will set the reminder for you automatically. When the time comes, you'll get a push notification or an email with the message.

Examples I've successfully tested: