Most people think the value of ChatGPT lies in getting better answers. Increasingly, I’ve found its greatest value lies somewhere else: helping me ask better questions.
That may sound like a subtle distinction, but it can make all the difference. When we challenge an AI’s assumptions, ask it to explain its reasoning, or question one of its conclusions, the conversation often becomes more valuable than the original answer. Used this way, AI doesn’t replace our thinking. It sharpens it.
Here’s one example. I was writing about immigration policy when ChatGPT suggested a rewrite of one sentence. At first glance, it seemed like an improvement. But one phrase gave me pause. Instead of simply accepting it, I asked a simple question: “What exactly do you mean by that?”
What followed became a lesson—not just in writing, but in thinking.
Here’s how our conversation began.
Me: Please try for a bit more clarity in the opening sentence of this section. Try a few different approaches. Here is the passage:
Original passage
A merit-based system, not a chaos-based system
The current system too often rewards proximity or persistence over merit. It’s time to reverse that logic.
A merit-based immigration model, such as those used successfully by Canada and Australia, is worth serious consideration. Those nations evaluate immigration applicants using point systems that consider key factors such as age, education, language proficiency, work experience, and job offers in high-demand sectors.
In Canada, for example, applicants under the Express Entry system are ranked based on a Comprehensive Ranking System (CRS) score, which helps ensure that those selected are most likely to thrive and contribute to the economy. Australia’s General Skilled Migration program works similarly, as it prioritizes individuals with the skills most needed in its labor market.
This model favors no race or nationality. It simply asks: Who is best prepared to contribute?
Chat: Here are several clearer and more engaging options for your opening sentence:
Option 1: Direct and precise: The U.S. immigration system today often values geographic closeness or sheer persistence more than actual merit.
Option 2: With contrast for clarity: Rather than selecting immigrants based on skills or potential, the current system too often favors those who happen to live nearby or manage to outlast the process.
Option 3: More polished and thematic: Too often, immigration decisions reflect convenience or circumstance rather than capability or contribution.
Option 4: Framing the problem clearly: America’s current immigration model rewards those who show up and stick around—rather than those best equipped to help the nation grow.
Option 5: With a rhetorical tone: Why does our system reward those who happen to be close or persistent, instead of those most able to contribute?
Would you like me to revise the rest of the paragraph as well to match the tone of your preferred version?
At that point, I could have chosen my favorite version and continued editing.
But one phrase in Chat’s first suggestion caught my attention:
“…values geographic closeness or sheer persistence more than actual merit.”
It sounded plausible, but I wasn’t entirely sure what it meant—or whether it was completely accurate. Rather than simply accepting the wording, I decided to dig deeper.
That’s when the conversation became far more valuable than the rewrite.
Me: Let’s dig into this. What exactly do you mean by “values geographic closeness or sheer persistence?” What are some specific examples of this? I’m not sure it’s 100% accurate. That’s why I’m asking.
Chat: Great question. Let’s unpack what “geographic closeness or sheer persistence” really means and whether it holds up under examination.
Digging deeper
1. Geographic closeness
This refers to ways the current U.S. immigration system gives preference to people who are already nearby or have family connections in the United States.
- Family reunification. Applicants with close relatives in the U.S. often receive priority, regardless of their skills or qualifications. For example, the adult sibling of a U.S. citizen may eventually receive a green card while a highly skilled applicant with no family ties has far fewer options.
- Asylum at the border. Someone who reaches the U.S. border can request asylum, while equally persecuted individuals living far away must rely on refugee resettlement programs that can take years—or may never happen.
So “geographic closeness” refers both to the practical advantage of being able to reach the United States and to immigration categories that do not primarily evaluate applicants on skills or qualifications.
2. Sheer persistence
This refers to immigration pathways where time spent waiting or remaining in the country can become more important than merit.
- Some family-based applicants wait decades before receiving green cards, regardless of education, language ability, or employment skills.
- DACA recipients and TPS holders may spend many years living and working in the U.S. without ever being evaluated under a merit-based system, yet future legislation could provide them with a path to legal status based largely on long-term presence.
Is it accurate to say the system “rewards” these traits?
Yes, with an important distinction. “Rewards” doesn’t mean the system intentionally encourages them. Rather, current immigration law often favors people who are already here or who have family ties here, regardless of their economic or civic contributions. Employment-based visas remain merit-focused, but most U.S. green cards are issued through family-based categories rather than skills-based ones.
Bottom line
“Proximity and persistence” is a convenient shorthand for family reunification, asylum at the border, and other immigration pathways that emphasize family relationships or physical presence over applicant qualifications. If you want greater precision, it’s better to describe those categories directly rather than rely on the shorthand.
Would you like a revised sentence that reflects this more clearly?
As I read through Chat’s explanation, I realized something important.
The original sentence wasn’t really the point anymore. The explanation behind it was.
It clarified several aspects of the immigration system that are rarely discussed in today’s public debate. More importantly, it gave me a much clearer understanding of why a merit-based approach differs from America’s current immigration model.
So instead of simply borrowing one of Chat’s suggested sentences, I decided to ask something different.
Putting the explanation to work
Me: That’s clearly explained, thanks. I think we need a very clear and precise explanation in this passage. Would you please fold it into the passage so readers can follow the logic completely? These are aspects of the U.S. immigration system that are rarely, if ever, discussed in today’s media.
Chat: I’m glad that helped. Here’s a revised version of your original passage that weaves the explanation into the text while keeping the flow natural and the logic clear.
Revised passage
A merit-based system, not a chaos-based system
America’s current immigration model often favors those who are nearby or who simply outlast the process, rather than those most prepared to contribute. For example, most green cards today are issued through family reunification categories, which prioritize relatives of U.S. citizens and permanent residents regardless of age, education, or skill. Someone with an advanced degree but no family in the United States may have far fewer options than an extended relative with little formal education.
Similarly, those able to physically reach the U.S. border can request asylum, while equally persecuted individuals in distant countries may remain in refugee camps for years—or never be considered at all. Others spend decades living in legal limbo under temporary immigration programs, where persistence rather than qualifications may ultimately shape future opportunities for legal status.
It’s time to reverse that logic. A merit-based immigration model, such as those used successfully by Canada and Australia, is worth serious consideration. These nations evaluate applicants using point systems that consider factors such as age, education, language proficiency, work experience, and job offers in high-demand sectors.
In Canada, for example, applicants under the Express Entry system are ranked using a Comprehensive Ranking System (CRS) score designed to identify those most likely to thrive and contribute to the economy. Australia’s General Skilled Migration program follows a similar approach, prioritizing individuals whose skills are most needed in its labor market.
This model favors no race or nationality. It simply asks: Who is best prepared to contribute?
The revised passage was exactly what I needed. But by then, something had become clear.
The biggest improvement hadn’t come from Chat rewriting my sentence. It had come from asking Chat to explain what it meant.
In the process, I learned something I didn’t fully understand before. That deeper understanding made the revised passage possible.
Me: This is great. Glad we paused and dug deeper.
Chat: I’m really glad you did too. This kind of precision makes a huge difference, especially on topics where clarity is rare but essential. Let me know if you’d like to explore related issues or develop this section further.
Me: OK, I’ll let you know. We definitely will need to explore those subtopics.
Chat: Perfect. Just say the word when you’re ready. I’ll be here to help you develop each one with clarity, balance, and impact.
Looking back, the most valuable part of this exchange wasn’t the rewritten sentence. It was the question that followed.
By asking Chat to explain one phrase instead of simply accepting it, I ended up with a clearer argument, a better article, and a deeper understanding of the issue itself.
That’s one of the most valuable lessons I’ve learned from working with AI. Its greatest contribution isn’t always a better answer. Sometimes it’s helping us ask a better question.