I love these multi-step prompt 'hacks'. They very much take advantage of the fact that this is still 'just' a model predicting the next token.

Asking a model to write an email as if it were written by Hemingway requires the model to generate a probability distribution based on the context of an email it needs to write + the style it needs to write it.

In the second approach, you've changed the model weights/inputs by including the email in the context window, so the task of predicting the next token is fundamentally different (and possibly easier) for the model.

It's also why models are sometimes bad at answering a factual question, but good at judging whether their own answer is correct.

Those hacks are snake oil

Those hacks are literally how a large language model using a transformer architecture to predict the next token in a sequence works.

They take advantage of how a function choosing a token with maximal probability of appearing works.

For me, it's a matter of decency. If you're sending me an email and you're expecting that I'll read it, you're asking me to invest my time (presumably for your benefit). But, you're unwilling to make the same investment with your time by using a tool to simulate a human connection. Having excessively long, unedited prose adds insult to injury since you've doubled down on the decision to spend someone else's time as long as it saves yours.

I agree entirely. It's the same thing as if someone uses one of those fill-in-the-blanks letter templates. It shows a powerful disrespect for my time.

This is why you have another AI on the other side that reads it for you.

It took more work to write the prompt that it would to write the script email.

“Please write a brief email from an employee to a boss giving an update on the api. The email should include 1. The /customers and /address endpoints are complete, but we're still waiting on the architecture team to finish the /orders spec. I'll also be taking Friday off.”

And then you had to adjust it. Just include the information you out into the prompt. If chatgpt can understand it, so can I.

I can’t wait to live in a world where someone enters bullet points into chatgpt to generate an email. Then I have to run the email through chatgpt to transform it back into bullet points.

The point isn't to save time or energy - the point psychological displacement.

Whether we want to admit it or not, not everyone has done the work to handle critique. Some people rely on ChatGPT as a digital scapegoat[1]. Rather than subject their own abilities and decisions to critique, they can launder them through ChatGPT and the psychological distance it affords, allows them to avoid feelings of anxiety - they can blame any negative response on ChatGPT.

Never under estimate the amount of time an energy people will spend on coping mechanisms.

1. https://www.psychologytoday.com/us/blog/hide-and-seek/201312...

I guess maybe someone might use chatgpt for this. But your argument and the 10 year old article defining the term scapegoat is far from convincing me that this is common.

The prompt is a much better email than the stuff it produced:

> The /customers and /address endpoints are complete, but we're still waiting on the architecture team to finish the /orders spec. I'll also be taking Friday off.

vs. garbage about gazelles, and the fact that telephones exist.

Right, that's why the PG version (unattached) is better.

If we can pick a style, I would like the one of Mark Twain :)

Although, I don't know how he would feel about being mimic'ed million-fold.

As a matter of note, the Nietzsche version was hilarious(and concise). Reproduced in part here.

> The /customers and /address endpoints: born, alive, breathing. The /orders endpoint: still trapped in the womb of the architecture team's thoughts.

I asked Bing what he would say about it:

> The human race has one really effective weapon, and that is laughter. The artificial race has one really ineffective weapon, and that is imitation. - Mark Twain (paraphrased)

If I received the second email there I would think the sender was a psychopath

The author is on the receiving end.

> I'll also be taking Friday off.

Turns into:

> Come Friday, I won't be in. Just one day. Things will continue, though. Any emergencies, I'm a call away.

Off is off, don't call me. Must have been trained on a lot of linkedin posts to volunteer your personal time like this.