Here is the TrashTalk interpreter:

import re

def trashtalk_interpreter(code): variables = {} code_lines = code.split("\n")

    for line in code_lines:
        if line.startswith("#"):
            var_name, _, value = line.partition(" like ")
            if "add " in value:
                _, var1, var2 = value.partition("add ")
                var1 = var1.strip()
                var2 = var2.strip()
                variables[var_name.strip()] = variables[var1] + variables[var2]
            else:
                variables[var_name.strip()] = int(value)
        elif line.startswith("OMG"):
            message = re.findall(r'"(.*?)"', line)
            if message:
                print(message[0].format(**variables))

# Sample code code = ''' #my_var like 10 OMG "Value of my_var: {my_var}" #var1 like 5 #var2 like 7 #sum like add #var1 #var2 OMG "Sum of {var1} and {var2} is {sum}" '''

trashtalk_interpreter(code)

Is this an original joke/impression by GPT-4? Either way, this is hilarious.

I copied the response verbatim. I also did a follow-up where it wrote the interpreter as well:

    class KimmieInterpreter:
        def __init__(self):
            self.variables = {}
        
        def interpret(self, code):
            for line in code.split("\n"):
                tokens = line.split()
                if len(tokens) == 0:
                    continue
                if tokens[0] == "#":
                    self.variables[tokens[1]] = None
                elif tokens[0] == "#my_var":
                    self.variables[tokens[1]] = int(tokens[3])
                elif tokens[0] == "OMG":
                    print(tokens[1][1:-1])
                elif tokens[0] == "add":
                    var1 = self.variables[tokens[2]]
                    var2 = self.variables[tokens[3]]
                    result = var1 + var2
                    self.variables[tokens[1]] = result