[terminalcommand]

For argument's sake I rewrote your prompt. I think gpt 3.5 understood it on the first try:

Prompt: Let’s play a cypher game.

The rules of the game are as follows:

1. Imagine a numbering system where each letter of the English alphabet corresponds to a number starting with 1. For example, a corresponds to 1, b corresponds to 2, c corresponds to three.

2. When you receive a word from me, break it into individual characters.

3. Convert each character into a list of numbers by following rule #1.

4. Subtract two from each number of the list and generate a new list, if the result is lesser than 0, add 26.

5. Convert each number in the new list into a letter by following rule #1 and present me your result.

Are you ready for the first word? ------- GPT: I'm ready! Go ahead and give me the word. Me: anthropomorfic GPT: Sure, let's start:

a -> 1 -> 1 - 2 = 25 (z)

n -> 14 -> 14 - 2 = 12 (l)

t -> 20 -> 20 - 2 = 18 (r)

h -> 8 -> 8 - 2 = 6 (f)

r -> 18 -> 18 - 2 = 16 (p)

o -> 15 -> 15 - 2 = 13 (m)

p -> 16 -> 16 - 2 = 14 (n)

o -> 15 -> 15 - 2 = 13 (m)

m -> 13 -> 13 - 2 = 11 (k)

o -> 15 -> 15 - 2 = 13 (m)

r -> 18 -> 18 - 2 = 16 (p)

f -> 6 -> 6 - 2 = 4 (d)

i -> 9 -> 9 - 2 = 7 (g)

c -> 3 -> 3 - 2 = 1 (a)

So, "anthropomorfic" becomes "zlrfpmmnpmkpdmga". Your turn!

[fireflash38]

Isn't 25 y not z?

[latexr]

Indeed it is. That part is a huge mess. The LLM gave the wrong number when matching with the letter, but the letter itself is correct considering the instructions, except the instructions are wrong (ironic considering this came from someone claiming everyone is doing it wrong). Step four says:

> Subtract two from each number of the list and generate a new list, if the result is lesser than 0, add 26.

It should be “if the result is less than 1”, not “0”.

[terminalcommand]

Well I told you I was bad at math. I wrote a faulty prompt. But chatgpt understood my instructions perfectly. That was the argument I was trying to demonstrate.

The problem lied between the chair and the computer.

We have to learn how to use LLMs.

[latexr]

> But chatgpt understood my instructions perfectly.

No, it did not, because it still assigned Z to 25, which is wrong.

> We have to learn how to use LLMs.

You have to learn that LLMs aren’t magical and will get things wrong no matter how much context you give them. And that the suggestions you’re making are absurd to the point of making them useless.