AI-assisted programming, an evolution of productivity

INLINE_CODE_0 发布也不到两年时间，INLINE_CODE_1 was released, and I don’t fully understand the underlying principles, but I’ve been using them for a while. The two tools offer completely different levels of assistance, but both significantly improve productivity.

For overly complex matters, the effect can only be about nine-tenths successful

github copilot

When it was released, the website description INLINE_CODE_0 didn’t seem very smart, and after trying it out, it wasn’t very usable, so I gave up

Before 2022, out of boredom, I switched to the new version for a try. The results are already pretty good, though the speed is slow in China, likely due to network issues. Code generated based on comments like Python is quite decent and much faster than researching and writing it myself.

ChatGPT

Still designing products from a programmer’s, or development, perspective. You need to understand how to code and gradually guide AI-assisted programming through comments.

Let non-experts quickly get started. The conversational, interactive design allows you to ask questions, describe your needs, and continue asking if anything is unclear.

For example, you understand the concept of tokenization but don’t know how to code it, and want to calculate string similarity

Python 分词计算 維天運通 LOGORY 和 合肥維天運通信息科技股份有限公司 两个字符串的相似度；
比较前，统一处理字符串，英文转换为小写；
第二个字符中如果能找到第一个字符的首字符，将第二个字符串截位，截位的长度为第一个字符串的长度

Hello, this is Bing. 😊

According to online information, Python tokenization can be implemented using the jieba library. Jieba supports three modes: precise mode, full mode, and search engine mode. You can choose the appropriate mode based on your needs.

To compare the similarity of two strings, you first need to tokenize them and then calculate indicators such as word vectors or edit distance. You can use libraries like NumPy or SciPy for mathematical operations.

To uniformly handle strings, converting them to lowercase can be achieved using Python’s built-in lower() function

To extract the second string, you can use Python’s slicing operator []

Here is a possible code example:

import jieba
import numpy as np
from scipy.spatial.distance import cosine

# 定义两个字符串
str1 = "維天運通 LOGORY"
str2 = "合肥維天運通信息科技股份有限公司"

# 统一处理字符串，英文转换为小写
str1 = str1.lower()
str2 = str2.lower()

# 找到第二个字符串中第一个字符的位置
index = str2.find(str1[0])

# 如果找到了，截取第二个字符串
if index != -1:
    str2 = str2[index:index+len(str1)]

# 使用 jieba 库进行分词
words1 = list(jieba.cut(str1))
words2 = list(jieba.cut(str2))

# 计算两个字符串的词向量（以词频作为权重）
vector1 = np.zeros(len(words1))
vector2 = np.zeros(len(words1))

for i, word in enumerate(words1):
    vector1[i] += 1 # 统计第一个字符串中每个词出现的次数
    if word in words2:
        vector2[i] += 1 # 统计第二个字符串中每个词出现的次数

# 计算两个字符串的相似度（以余弦距离作为指标）
similarity = 1 - cosine(vector1, vector2)

print("两个字符串的相似度是：", similarity)

Please provide the Chinese text you want me to translate. I am ready when you are!

Chestnut

Find all records from the product code table where the product codes are within the range of 80000-89999

你好，这是 Bing。😊

根据搜索结果12，你可以使用 SQL BETWEEN 运算符来选择给定区间内的值。BETWEEN 运算符包含了开始和结束的值。

你需要先指定要查询的表名和列名，然后在 WHERE 子句中使用 BETWEEN 运算符和区间值。

例如，如果你要查询产品代码表中，产品代码在 80000 到 89999 之间的记录，你可以使用以下语句：

SELECT * FROM product_code
WHERE code BETWEEN 80000 AND 89999;
这里，* 表示选择所有列3。如果你只想选择特定的列，比如产品名称和价格，你可以用逗号分隔它们，如下：

SELECT name, price FROM product_code
WHERE code BETWEEN 80000 AND 89999;
希望这能帮助到你。

Keep asking, deny it: The product code is a string, your code is wrong

抱歉，我没有注意到产品代码是字符串。如果是这样的话，你需要在区间值两边加上单引号，如下：

SELECT * FROM product_code
WHERE code BETWEEN '80000' AND '89999';
请原谅我的错误。🙏

Congratulations, it will be wrong