In the era of ChatGPT, programmers continue to be popular

Many programmers use ChatGPT just to write a small script and write a small function, thinking that it is nothing more than that, they may not think that the ability of ChatGPT to generate code is far beyond your imagination!

Our planet "ChatGPT base" has organized a big sailing event, let's explore how awesome ChatGPT is.

The creativity of the golfers was overwhelming, and many excellent projects emerged. The following are a few award-winning projects.

1. Use natural language to describe the interface structure, and let ChatGPT generate complex interfaces

a677edb51137ee26b78830c0c7a09a90.png

2. An Android pure novice, with the help of the ChatGPT teacher, develops an APP, regularly reads the mobile phone text messages, and pushes them to his own server.

c785a14b73ad1af97d7b56b30f5730f6.png

3. Use ChatGPT to develop a simple rich text editor

49a43cd341c5050618270d1ceb395c85.png

4. With only a basic understanding of Python, use ChatGPT to implement a thousand-character text prompter

8f6e6e688392be695568ebcbecbdb924.png

5. Use ChatGPT to realize barcode recognition

976c4656f80fc9f29ca3971ad0f062de.png

6. Use the ChatGPT API to implement a voice-interactive online chat question-and-answer service

f7b2c8b0d28eaac092e9b3bf9c635f98.png

They cover programming languages ​​such as HTML, CSS, JavaScript, Python, Java, C#, front-end, back-end, Android, scripting and other fields.

These are nothing, what is surprising is that:

These small projects basically do not write code, and are generated using natural language and ChatGPT interaction!

I think using ChatGPT programming can be divided into three levels:

1. Function level

This is easy to understand, it is a specific function

2. Module level

Involving the interaction of multiple classes and multiple functions, the projects of Dahanghai are relatively small and can be classified into this level.

3. System level

Large IT systems, such as e-commerce systems.

For function-level code, many people have realized that ChatGPT is a piece of cake to implement and can be easily done. Specific and well-defined needs are areas where ChatGPT is very good at now.

At the module level, I said in " Programmers Can Rest assured ", ChatGPT can generate 95% of the runnable code, and the remaining 5% needs the guidance of the programmer. The programmer needs to judge whether it is correct, especially some special In some cases, the AI ​​is not thoughtful and relies on the insight of the programmer.

At the system level, ChatGPT is fooled, for example, if you tell it:

I want to create an e-commerce system, including user management, product management, order management, warehouse management and other common functions. It needs to support flash sales activities, coupons, points system and other functions. Help me write out the code.

ChatGPT is absolutely impossible for you to achieve, such a demand is too big, too vague.

(Of course, this cannot be said too much. Now the large model is developing extremely fast, and the "emergence ability" is very amazing, such as good class design ability. In December last year, GPT-3.5 was not enough. This year's GPT- 4 is already very powerful.)

Based on this analysis, at this stage, my positioning of programmers in the ChatGPT era is:

It can decompose complex requirements into modules, and then drive and guide ChatGPT to realize it.

In the ChatGPT era, a very important value of the programmer profession is to judge whether the code output by ChatGP is correct or not, and guide it to make changes. This job is impossible for laymen.

If you simply get a demand to realize, it may still exist, but the value is very low, and the corresponding salary may also be very low.

Finally, let’s promote the planet "ChatGPT base" established by Shanke and I, which is dedicated to exploring the position of programmers in the ChatGPT era and how to use ChatGPT to improve work efficiency.

In the field of programmers, our planet may be the most deeply engaged in ChatGPT . It has gone far beyond the ChatGPT chat stage. Many people have entered API development and even privatized model training.

ChatGPT chat -> use ChatGPT API to develop applications -> train privatization and deploy large models

Many friends here have evolved from Xiaobai to skilled players in the field of ChatGPT. Planet’s column has many valuable topics:

f6a0aaa6e2e284608b6021a086c8d908.png

Come to this planet, brush your heart for a few days, and you will surpass 99% of people in this field without knowing it.

The planet now has these events:

Join the planet to get a ChatGPT account (only for the top 100 who entered the planet today, contact information: add WeChat onlyliuxin97 )

Export high-quality content and send a 100 yuan red envelope

Participate in the check-in challenge and have the opportunity to refund the star fee

This Saturday Planet Ball Friend @赵学习 will bring you Planet’s first live broadcast sharing. The theme is to use ChatGPT to quickly build a blog site + privatize a large model for local deployment . Join Planet to watch this live broadcast together. Go to You will be notified in the pinned announcement from time to time.

Now the planet is in the trial operation period, the original price is 199 yuan, now there is a coupon of 100 yuan , which is equivalent to 99 yuan , you can join, embrace ChatGPT early, become the first batch of people who can use ChatGPT and use ChatGPT well, and take the lead , get bonus.

6e4a3943fef4e655ab0f28308676dba6.png

Guess you like

Origin blog.csdn.net/coderising/article/details/130278758