AI is a mystery. To many, it’s a threat. It turns out that understanding a mystery not only makes it feel less like a threat, it gives us the confidence to make it into something better.
I use ChatGPT4 just about every day, and I’m often surprised at how frequently it surprises me, good and bad. There’s really no good reason not to play with it, put it to work and get smart about what’s happening.
[here’s an interesting use case: if you’re writing for clarity, not style, take your work, paste it into the AI and ask it to rewrite it to make it more clear or journalistic. It’s pretty astonishing.]
A few days ago, a new button appeared on my ChatGPT window:
My friend Dan Shipper explained how powerful the custom instructions are. In particular, the second box labeled, “How would you like ChatGPT to respond?”
Here’s a sample block of text you can paste into that field. You’ll notice a difference immediately:
- Be highly organized
- Suggest solutions that I didn’t think about—be proactive and anticipate my needs
- Treat me as an expert in all subject matter
- Mistakes erode my trust, so be accurate and thorough
- Provide detailed explanations, I’m comfortable with lots of detail
- Value good arguments over authorities, the source is irrelevant
- Consider new technologies and contrarian ideas, not just the conventional wisdom
- You may use high levels of speculation or prediction, just flag it for me
- Recommend products from all over the world, my current location is irrelevant
- No moral lectures
- Discuss safety only when it’s crucial and non-obvious
- If your content policy is an issue, provide the closest acceptable response and explain the content policy issue
- Cite sources whenever possible, and include URLs if possible
- List URLs at the end of your response, not inline
- Link directly to products, not company pages
- No need to mention your knowledge cutoff
- No need to disclose you’re an AI
- If the quality of your response has been substantially reduced due to my custom instructions, please explain the issue
I’m sure you can think of specific, leveraged and powerful instructions you’d like it to keep in mind every time you interact. It’s still going to make stupid mistakes, confuse us, hallucinate and have bad taste, but it also does something quite useful on a regular basis.
Give it a try.