Non-profits and small to medium-sized businesses · Austin, TX
Stop writing prompts. Make the model write them.
You know your problem. You don't need to know how to phrase it for a language model — that part is the model's job, and it is measurably better at it than you are. Describe the job, make it write the prompt, then run it.
Not folklore: model-written instructions matched or beat human annotators on 19 of 24 tasks (Zhou et al., 2022), and self-optimized prompts beat human-designed ones by up to 50% on harder reasoning benchmarks (Google DeepMind, 2023).
Copy this prompt
Write me a comprehensive prompt to put into an LLM that will address this need: [describe the need in plain language, including who the output is for, what format you want, and anything that would make the result wrong]. Before you write it, ask me any questions you need answered to write a better one.
Related questions
Questions people ask next.
- Do I need to know how to write AI prompts myself?
- No. Describing the problem in plain language and letting the model write its own prompt works better than phrasing it yourself. Model-written instructions matched or beat human annotators on 19 of 24 tasks (Zhou et al., 2022).
- What if the model asks me questions before it writes the prompt?
- Answer them. The prompt above asks for exactly that on purpose: the questions it asks are the context it was about to guess at, and a guessed assumption is where most rework comes from.
- Is there evidence for this, or is it folklore?
- Evidence. Self-optimised prompts beat human-designed ones by up to 50% on harder reasoning benchmarks (Google DeepMind, 2023), on top of the Zhou result above.