The typical blueprint for prompt engineering: ✍️ Make your request as detailed as possible. Ask the model to break things down step-by-step, so it doesn’t get confused. And instill confidence by emphasizing its expertise in the subject matter. 💡
But with its new reasoning-focused model, OpenAI is asking us to turn that conventional wisdom on its head. 🔄 The reason? o1 does most of the heavy lifting on its own, so cluttering it with complicated prompts can lead to lower-quality outputs. 🚫
Here are some tips, adapted from OpenAI’s API Documentation: 📚
âś… Keep prompts simple and direct
✅ Avoid “chain-of-thought” prompts (i.e. “explain your reasoning”), since the model does most of its thinking internally
✅ Don’t clutter your prompts with too much information; only include what’s most important
Example related to STEM research:
🧪 Prompt: What are three compounds we should consider investigating to advance research into new antibiotics? Why should we consider them?
🤔 Question for You: How do you think simplifying prompts can enhance the quality of AI-generated responses? Share your thoughts! 💬