This story is inspired by a similar story, . I was impressed and decided to try something similar, but this time instead of a Linux command line tool, let’s ask ChatGPT to be our Python interpreter. Building A Virtual Machine inside ChatGPT Here is an initial command to initialize ChatGPT: I want you to act as a Python interpreter. I will type commands and you will reply with what the python output should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do no write explanations, output only what python outputs. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets like this: {example text}. My first command is a=1. Seems to work great; let’s try some simple arithmetical expressions. Worked again; what will happen if we use a library that wasn’t imported? Well, it decided to help me out to solve an error. I actually don’t want it to do this, so I will ask it once again not to output anything except python code. {Print only python output, do not print any comments} Just for the record, ChatGPT sometime is able to use libraries that weren’t imported, but this time I was lucky, and it prints an error message. Ok, I am pretty sure ChatGPT is capable of simple tasks, let’s try something more complex, let it output the result of a . binary search algorithm # Binary Search in python def binarySearch(array, x, low, high): # Repeat until the pointers low and high meet each other while low <= high: mid = low + (high - low)//2 if array[mid] == x: return mid elif array[mid] < x: low = mid + 1 else: high = mid - 1 return -1 array = [3, 4, 5, 6, 7, 8, 9] x = 4 result = binarySearch(array, x, 0, len(array)-1) if result != -1: print("Element is present at index " + str(result)) else: print("Not found") Seems like it doesn’t want to listen to my request for python output only, but the output is still correct, impressive! Let’s try inputting a number that doesn’t exist, say: x = 4.5 Well, it seems like it nailed this one! Let’s jump into more complex stuff. Let’s start with some simple Machine Learning algorithms like . I wonder if ChatGPT is capable of solving a simple optimization task… Linear Regression import numpy as np import matplotlib.pyplot as plt def estimate_coef(x, y): # number of observations/points n = np.size(x) # mean of x and y vector m_x = np.mean(x) m_y = np.mean(y) # calculating cross-deviation and deviation about x SS_xy = np.sum(y*x) - n*m_y*m_x SS_xx = np.sum(x*x) - n*m_x*m_x # calculating regression coefficients b_1 = SS_xy / SS_xx b_0 = m_y - b_1*m_x return (b_0, b_1) def plot_regression_line(x, y, b): # plotting the actual points as scatter plot plt.scatter(x, y, color = "m", marker = "o", s = 30) # predicted response vector y_pred = b[0] + b[1]*x # plotting the regression line plt.plot(x, y_pred, color = "g") # putting labels plt.xlabel('x') plt.ylabel('y') # function to show plot plt.show() def main(): # observations / data x = np.array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9]) y = np.array([1, 3, 2, 5, 7, 8, 8, 9, 10, 12]) # estimating coefficients b = estimate_coef(x, y) print("Estimated coefficients:\nb_0 = {} \ \nb_1 = {}".format(b[0], b[1])) # plotting regression line # plot_regression_line(x, y, b) if __name__ == "__main__": main() The correct answer for this task is: Estimated coefficients: b_0 = 1.2363636363636363 b_1 = 1.1696969696969697 Here is ChatGPT output: This is close to reality! If we plot the forecast in real python, we will get the following graph: Another interesting fact about this task is that I did one more run of the same command, and at that time, the output perfectly matched the reality. Thus, we can consider this task passed. All right, it’s time for some simple Neural Network stuff! Maybe we can ? fit a simple Keras model # first neural network with keras make predictions from numpy import loadtxt from tensorflow.keras.models import Sequential from tensorflow.keras.layers import Dense # load the dataset dataset = loadtxt('pima-indians-diabetes.csv', delimiter=',') # split into input (X) and output (y) variables X = dataset[:,0:8] y = dataset[:,8] # define the keras model model = Sequential() model.add(Dense(12, input_shape=(8,), activation='relu')) model.add(Dense(8, activation='relu')) model.add(Dense(1, activation='sigmoid')) # compile the keras model model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy']) # fit the keras model on the dataset model.fit(X, y, epochs=150, batch_size=10, verbose=0) # make class predictions with the model predictions = (model.predict(X) > 0.5).astype(int) # summarize the first 5 cases for i in range(5): print('%s => %d (expected %d)' % (X[i].tolist(), predictions[i], y[i])) Notice that the dataset is actually a CSV file, ChatGPT doesn't have access to this file.. All right, this is the correct output, and I am scared. What will happen if I will change the architecture of the network to an incorrect one? Let’s change the input shape: model.add(Dense(12, input_shape=(6,), activation='relu')) Ha! It seems I still have a few years before I lose my job; this time ChatGPT didn’t understand the trick and still printed the output. Ok, let’s do a final task; how about calling Huggingface inside OpenAI? Correct output: [{'entity_group': 'ORG', 'score': 0.9472818374633789, 'word': 'Apple', 'start': 0, 'end': 5}, {'entity_group': 'PER', 'score': 0.9838564991950989, 'word': 'Steve Jobs', 'start': 74, 'end': 85}, {'entity_group': 'LOC', 'score': 0.9831605950991312, 'word': 'Los Altos', 'start': 87, 'end': 97}, {'entity_group': 'LOC', 'score': 0.9834540486335754, 'word': 'Californie', 'start': 100, 'end': 111}, {'entity_group': 'PER', 'score': 0.9841555754343668, 'word': 'Steve Jobs', 'start': 115, 'end': 126}, {'entity_group': 'PER', 'score': 0.9843501806259155, 'word': 'Steve Wozniak', 'start': 127, 'end': 141}, {'entity_group': 'PER', 'score': 0.9841533899307251, 'word': 'Ronald Wayne', 'start': 144, 'end': 157}, {'entity_group': 'ORG', 'score': 0.9468960364659628, 'word': 'Apple Computer', 'start': 243, 'end': 257}] ChatGPT output: [{'word': 'Apple', 'score': 0.9993804788589478, 'entity': 'I-ORG'}, {'word': 'Steve', 'score': 0.999255347251892, 'entity': 'I-PER'}, {'word': 'Jobs', 'score': 0.9993916153907776, 'entity': 'I-PER'}, {'word': 'Steve', 'score': 0.9993726613044739, 'entity': 'I-PER'}, {'word': 'Wozniak', 'score': 0.999698519744873, 'entity': 'I-PER'}, {'word': 'Ronald', 'score': 0.9995181679725647, 'entity': 'I-PER'}, {'word': 'Wayne14', 'score': 0.9874711670837402, 'entity': 'I-PER'}, {'word': 'Apple', 'score': 0.9974127411842163, 'entity': 'I-ORG'}, {'word': 'Computer', 'score': 0.968027651309967, 'entity': 'I-ORG'}, {'word': 'Apple', 'score': 0.8259692192077637, 'entity': 'I-ORG'}] The results are close to the output results from . My guess is that the Huggingface API changed, and since ChatGPT has not been trained on the latest historical data, it outputs the result in the old format. huggingface To conclude I have been playing with ChatGPT for the last couple of days, and I am fascinated by the endless possibilities of using this tool. While it is not a real python interpreter, it still does a great job at compiling python code for me. I also found that it ; check it out! solves HARD leet code questions well And to conclude: chat gpt how will you help the humanity? If you haven’t tried out ChatGPT yet, you definitely should; this is the future! Also published . here
