OpenClaw, Hermes, Poke를 쓰며 느낀 단점들

내가 만약 워크스페이스 에이전트를 만든다면 어떻게 만들까?

메모리

• 육하원칙에 맞게 기억해야하는데, 이걸 잘 못 함
  • 맥락을 종종 헷갈려함
• 메모리 툴을 명시적으로 불러야 함
  • 이는 Hermes에서 많이 완화된 부분

Slack

• 답장을 매번 하려 함. 쓰레드에 달리는 모든 글에 답을 함.
  • 매번 답할 필요는 없음. 필요할 때만 하면 됨.
• 언급하지 않은 메시지는 읽지 않음.
  • 모든 워크스페이스의 변화를 계속 보고 있어야 함, 그리고 기억해야 함

Solved at: 220710

Question

• Two Sum - LeetCode

Given an array of integers nums and an integer target, return indices of the two numbers such that they add up to target. You may assume that each input would have exactly one solution, and you may not use the same element twice. You can return the answer in any order.

Solution

So the first obvious answer is to iterate twice. This finishes calculations in $O(n^2)$ time.

class Solution:    def twoSum(self, nums: List[int], target: int) -> List[int]:        for idx1, val1 in enumerate(nums):            for idx2, val2 in enumerate(nums):                if idx1 == idx2:                    continue                if val1 + val2 == target:                    return [idx1, idx2]

However, this gives a timeout.

Improved

I used Python Dictionary to store complementing values. Python Dictionary will have $O(1)$ access time for most cases. This solution will run in $O(n)$ time.

• One caveat: depending on the hash function, it can go as bad as $O(n^2)$.

class Solution:    def twoSum(self, nums: List[int], target: int) -> List[int]:
        # map for complementing elements: complementary-idx        complementing_map = {}
        for idx, val in enumerate(nums):            if val in complementing_map:                return [complementing_map[val], idx]            complementing_map[target - val] = idx

Results

Runtime

• 60 ms, faster than 97.16% of Python3 online submissions for Two Sum.

Memory Usage

• 15.4 MB, less than 14.24% of Python3 online submissions for Two Sum.

Other Answers Online

• Sort first, $O(n \log n)$
• For all elements, $O(n)$
  • Perform binary search $O(\log n)$
• In total: $O(n \log n)$