New Disclaimer for Email Signatures and other Written Material?

At the end of his most recent email, “AI and You,” @MacSparky had this line, ”P.S. Not a single word of this newsletter was written with any sort of AI.” Perhaps we should add a similar disclaimer to our email signatures, articles, and posts. :slightly_smiling_face:


I asked ChatGPT for an email disclaimer. It gave me this:

Dear [Recipient],

I would like to clarify that this email was composed by me, [Your Name], and not by an AI assistant. While technology has made it possible to automate many tasks, I believe that direct communication between people is essential for building strong relationships and fostering trust. As such, I want to assure you that this message reflects my thoughts and feelings, and that I am personally invested in our correspondence.

Thank you for your understanding and I look forward to hearing from you soon.

Best regards,
[Your Name]


Hmmm, that’s longer than most of my emails. :slightly_smiling_face: But, not a bad disclaimer.


I may go with, “No intelligence, artificial or otherwise, was employed in the composition of this message.”


You made my day; I’m laughing hysterically! :rofl:

1 Like

Well played, Siri! :slight_smile:


Except the disclaimer was all AI, so the email was partially composed by an AI assistant. :slight_smile:


Just end it with the classic: This statement is a lie.

1 Like

Written with what came to my mind.

That’s going to be my disclaimer.

Not quite the same, but I had a disagreement with someone on Mastodon recently in this space.

Their position was any AI-generated text/article should be required to be labelled as such, as “there are plenty of people out there with no common sense”.

However, I think it will have no net effect, because those same people “with no common sense” will take the absence of the mark to mean it is trustworthy. I think it is pretty clear that AI didn’t invent online nonsense; people (not machines) have been churning it out for years. We call the worst of them conspiracy theorists.

I think the better disclaimer would be Trust nothing I say. That can be used whether AI-generated or not.

1 Like

What people don’t seem to get is that AI is generated based on information that it has found on the Internet. In other words, the incorrect opinions of AI are generally the incorrect opinions of actual people first.

The problem is that AI doesn’t know whether it’s copying a genius or an idiot.

The fact that something is generated by a human is, therefore, no additional guarantee of accuracy or utility. :slight_smile:

1 Like

Do people use disclaimers in their personal mail? (I don’t)

(At work it is a standard text, written by people outside my circle of influence)

I’m waiting for a court case testing the legality of email disclaimers.

1 Like

IMO any message that needs to be “protected” by a disclaimer should not be sent by email. I have seen them described as “the modern equivalent of mattress tags”.

They do and some of them are MUCH longer than the email text. I find them frustrating. It seems to me, assuming disclaimers have any legal standing at all, that it would be nicer to have a text link to a disclaimer so that the reader is notified and has the option to read it if he or she chooses. Long disclaimers are a minor pet peeve of mine. :slightly_smiling_face:

Only thing worse (in this realm) is image signatures that flag the email as having attachments.


But what am I going to do if my employer requires a standard format for my signature and appends one of those long “delete this if you are not the intended recipient or received this e-mail in error” kind of message? :slightly_smiling_face:

There is nothing you can do, especially if the disclaimers are automatically attached to your outbound messages.

Just think about the joy they bring to those people who receive messages from your company in error, when they laugh at the “ delete this . . . instructions” attached to your message. :grinning:

1 Like

Those “delete this misdelivered email” disclaimers always make me think of how the New York Times may once have gotten a scoop about a billion-dollar pharmaceutical settlement because of a lawyer’s email goof…


I’m sure you could get ChatGPT to do the disclaimer for you.