I recently got access to Github's Copilot and it struck me that it could generate a lot of algorithms that someone might not know or even solve some of the simpler problems with ease. Despite this technology being very new, I think it's worth adding a rule restricting or prohibiting the use of certain AI code completers. From what I'm seeing in the development of this field, it's only a matter of years before someone trains an AI that can perform in coding contests at a LGM level.
Examples to demonstrate the power of Copilot:
- A very classical finding the maximum subarray of an array. (Kadane's Algorithm)
What was given: ~~~~~ nums = [6, 7, -2, 4, -4, 6, 12, 5]
find max subarray
What was generated:
max_sum = float('-inf') current_sum = 0 for i in range(len(nums)): current_sum += nums[i] if current_sum > max_sum: max_sum = current_sum if current_sum < 0: current_sum = 0
print(max_sum) ~~~~~
- Find 2 elements in an array that equal to N (2 Pointers) What was given: ~~~~~ nums = [6, 7, -2, 4, -4, 6, 12, 5]
Find a pair of numbers that sum to n.
What was generated (1st solution):
def pair_sum(nums, n): seen = set() output = set() for num in nums: target = n — num if target not in seen: seen.add(num) else: output.add((min(num, target), max(num, target))) return len(output)
Second Solution (brute force)
def find_pair(nums, n): for i in range(len(nums)): for j in range(i + 1, len(nums)): if nums[i] + nums[j] == n: return nums[i], nums[j] return None ~~~~~
- Coin Change
coins = [1, 2, 4, 5, 9, 69, 420]
# minimum number of coins needed to make n cents
# dynamic programming
def minCoins(n):
if n < 0:
return 0
elif n in coins:
return 1
else:
return 1 + min(minCoins(n-i) for i in coins if i <= n)
=======
def min_coins(cents):
for cents in range(1, cents+1):
for coin in coins:
if coin <= cents:
num_coins[cents] = min(num_coins[cents], num_coins[cents-coin] + 1)
return num_coins[cents]
=======
def coin(n):
coin_count = [0] * (n+1)
coin_count[0] = 0
for coin in coins:
for i in range(coin, n+1):
coin_count[i] += coin_count[i-coin]
return coin_count[n]
=======
def min_coins(n):
table = [0] + [10000] * n
for i in range(1, n + 1):
for j in coins:
if i >= j and table[i - j] + 1 < table[i]:
table[i] = table[i - j] + 1
return table[n]