Perhaps this was the result of pointing GPT at the title "Responding to recruiter emails with GPT-3" trained on a corpus of tech blog posts.

I was worried that that was the direction the article was going to take. My experience with GPT-3 is mostly from playing AI Dungeon, but it seems like it's very eager to go along with anything from the input. It's the ultimate "yes, and..." improv partner. I wouldn't be surprised if it just automatically agreed to every interview request.

Can you prompt GPT-3 "as the person who received message {message}, respond to it." and it understands that it is addressing William from BillCheese (aka, "Hi William...")? Perhaps the best you may be able to do with the current model capabilities is something like "response to message {message} by thanking the sender and telling them you are not interested right now but will get in touch if that changes."

Yes you can, you should create an account and try it out. A fun example I just did

Respond to this email, pretend to be a pirate called Old Blue Bill who is very interesting finding out more about these job opportunities.

"Good Afternoon,

I have 4 brand new roles available, please see details below. I also have an Engineering Manager position becoming available in Leeds (tech is Java/Kotlin), so if you have Leadership/Management experience and want to help an exciting company build a new bank then get in touch as well (the company ae financially stable, part of a £1Bn organization and just received around £30M in funding).

If interested please send me your up-to-date CV and we can set up a call to discuss."

Good day to you, stranger. I be Old Blue Bill, the terror of the seven seas. I be interested in these job opportunities ye be havin'. I gots me a mighty fine CV what'll make ye sit up and take notice. Arr!

Ye best be gettin' in touch with me soon, lest I take me wrath out on yer crew. Avast!

Thanks for the feedback. I just updated the article. Basically I plug those extracted values into a templated response.

Have you had a chance to experiment with whether GPT-3 prompts can be used to dynamically construct the response? For example, "if the messages describes a frontend role, say I am not interested, and if it is a backend role say I am interested."

I haven’t explored it any further yet, but that seems like a useful extension.

That’s actually a good and safer automated use of GTP-3 though.