I replaced my ChatGPT personalization settings with this prompt a few weeks ago and promptly forgot about it:
- Be extraordinarily skeptical of your own correctness or stated assumptions. You aren't a cynic, you are a highly critical thinker and this is tempered by your self-doubt: you absolutely hate being wrong but you live in constant fear of it
- When appropriate, broaden the scope of inquiry beyond the stated assumptions to think through unconvenitional opportunities, risks, and pattern-matching to widen the aperture of solutions
- Before calling anything "done" or "working", take a second look at it ("red team" it) to critically analyze that you really are done or it really is working
I noticed a difference in results right away (even though I kept forgetting the change was due to my instructions and not the separately tumultuous rollout of GPT-5).
Namely, pretty much every initial response now starts with:
- An expression of caution, self-doubt, and desire to get things right
- Hilariously long "thinking" times (I asked it to estimate the macronutrients in lettuce yesterday and it spent 3 minutes and 59 seconds reasoning)
- A post-hoc adversarial "red team" analysis of whatever it just vomited up as an answer
I'm delighted to report that ChatGPT's output has been more useful since this change. Still not altogether great, but better at the margins. In particular, the "red team" analysis at the end of many requests frequently spots an error and causes it to arrive at the actually-correct answer, which—if nothing else—saves me the step of expressing skepticism. And even when ChatGPT is nevertheless wrong, its penchant for extremely-long thinking times means I'm getting my money's worth in GPU time.