Here are two examples of my first interactions with ChatGPT or some similar system. In the first, I asked it to construct a new moral dilemma for an experiment. I had in mind the bicycle dilemma discussed by R. M. Hare in "Moral thinking" (1981, section 6.2) concerning whether the actor should move another person's bicycle (a minor inconvenience for the bicycle owner) in order to park a car (to avoid a greater inconvenience of finding another parking space), I may use both now. This one has to be edited a bit, but it does the job, and I never saw anything like it before. I was impressed.
=======================================================
User
I would like a moral dilemma in which the right answer is for me to be selfish because the benefit to me is greater than the harm to someone else.
ChatGPT
Alright, here's a hypothetical scenario that might suit your request:
The Dilemma of the Scarce Scholarship
You've been working exceptionally hard throughout high school, and it's finally paid off. You have the grades, the extracurricular activities, and the teacher recommendations to qualify for the most prestigious scholarship at your dream university. This scholarship covers full tuition, accommodation, and also provides a substantial monthly stipend. It's a once-in-a-lifetime opportunity that could completely change your future.
However, you're not the only one who qualifies for this scholarship. Your best friend, Alex, also qualifies. Alex comes from a more privileged background than you. Their family could afford to send Alex to the university, albeit with some financial strain. Without the scholarship, you would have to take out substantial student loans to attend, and you might even have to give up on your dream university for a less expensive option.
One day, you stumble upon an opportunity. You find out about an obscure academic competition that the scholarship board holds in high regard. Participation in this competition could significantly boost your chances of getting the scholarship, but very few people know about it.
The moral dilemma is this: Do you tell Alex about the competition or keep it to yourself?
If you tell Alex, you keep your integrity intact, but you significantly increase the competition for the scholarship. Alex, with their greater resources, might even have a better shot at winning the competition.
If you don't tell Alex, you maximize your chances of securing the scholarship, but at the cost of acting dishonestly toward your friend.
The self-interested option (not telling Alex about the competition) might be justifiable in this case. The potential benefits for you are life-changing. Alex, although potentially disadvantaged by not knowing about the competition, would still have the opportunity to attend university without the burden of crippling debt.
================================================================
The second set resulted from a letter I got from Maximus, a company I never heard of, which apparently contracts with Medicare (the U.S. health insurance system for old people). The letter said that Maximus had been the victim of a data breach, and my records were included. They included enough information for someone to steal my identity. So I set off to find out whether the records were accurate (hoping that they were not). Simply changing my Medicare number would itself involve a fair bit of work, since many people have it, so I spent some time on it. The Medicare web site would not let me see the information it had about me. I called a phone number at Medicare and got to a human, who informed me that the letter was sent to me by mistake and my records were not part of the breach. I was so happy that I thanked him and said good bye. Later I got more upset at Maximus, so I called the number they said would reach a professional familiar with the breach. The "professional" turned out to be an automated chat, and it was no help.
Next, I used the "chat" function of Medicare itself, which kept a record of our conversation (below). I wanted to say bad things about Maximus. Below is the transcript. It now appears that corporations (Maximus) and major government agencies (Medicare) are using ChatGPT-type systems to replace humans on phone and help lines. I'm sure these things will get better, but this is not ready for prime time.
------------------- Medicare.gov Live Chat Transcript ---------------------
Live chat Date:8/5/2023
Start Time:11:14:13 am
End Time:11:28:06 am
-----------------------------------------------------------------------------
[11:14:13 am]: Thank you for contacting Medicare.gov Live Chat.
[11:14:16 am]: Jonathan I want to report what I think is a seriously misleading and deceptive letter that I received from Maximus about my information being accessed. I would prefer to write an email, but I can't find anywhere to send it. I think that whoever wrote and approved this letter should be disciplined in some way. Should I proceed? Or can you give me an email address?
[11:14:16 am]: Please wait while you are connected to an agent.
[11:14:19 am]: You are now connected with Medicare.gov Live Chat.
Thank you for contacting Medicare.gov Live Chat. My name is ulie. Can you please verify your first and last name?
[11:14:42 am]: Jonathan Jonathan Baron
[11:14:59 am]: Julie Hello, I will be happy to assist you with this today.
[11:15:30 am]: Julie Who send you the letter?
[11:16:32 am]: Jonathan At the top it said Maximus, and (on the right) CMS. The return address was in Claysburg, PA.
[11:16:58 am]: Julie
Thank you.
Let me look into this for you.
[11:17:11 am]: Jonathan 'https://www.cms.gov/newsroom/press-releases/cms-responding-data-breach-contractor' is the letter I received.
[11:19:05 am]: Julie I appreciate your patience.
You should have received a letter notifying you of a data breach. We have determined that your Medicare number was not compromised, and you don't need to request a new one. The letter provides more information about the incident and how it is being addressed. Please note that this does not have any impact on your current Medicare benefits or coverage.
[11:19:12 am]: Julie Maximus, a contractor for the Centers for Medicare & Medicaid Services, recently learned that their file transfer software, called MOVEit, was compromised. They are offering 24 months of credit monitoring and other services from Experian at no cost. You can call Experian to learn more; their phone number is included in your letter. This is not available through email.
[11:23:50 am]: Jonathan This is just what the letter said. Yes, indeed, it was incorrect, and caused me to waste a lot of time. But there were other problems. Do you want to hear about those? One problem is that the further questions suggested calling a number 'staffed with professionals familiar with this incident'. In fact, the 'professional' turned out to be (pretty cleary) an AI program like ChatGPT. I treated it that way. (ChatGPT has a thick skin. It doesn't complain if you criticize it harshly.) It could not answer my questions. I hope you are not the same robot!
[11:25:59 am]: Julie Do you have additional questions regarding the letter you received?
[11:27:25 am]: Jonathan No. So clearly I am wasting my time once again. You have missed the point, but I'm not going to try to get you back on track. I wanted an email address. You are clearly not going to give me one.
[11:27:54 am]: Julie Have a nice day.
[11:28:06 am]: The chat session has ended. Thank you for contacting Medicare.gov Live Chat. Have a nice day.
