ChatGPT - A personal programmer?
Photo by Andrea De Santis on Unsplash

ChatGPT - A personal programmer?

I had been trying ChatGPT for a few basic needs, like summarizing an article, writing better emails, getting structured approaches for tackling different problems. It was helpful and saved some time.

Then, I read about how it could help in programming. Could ChatGPT really provide an entire program for any request thrown at it, a la a personal programmer? That would be something.

I tried using it for a personal project that I’d shelved previously - it seemed too complicated (for me) at that time.

After running through different prompts, ChatGPT finally figured out what I was looking for (or, I was able to explain it better). And then the programs started coming through. Within an hour, I had code to read music files, another one to update their tags, yet another one to build a folder of album art etc. It was glorious.

A few notes.

  1. No starting trouble - ChatGPT was able to get started right away - it set the initial libraries, provided a high-level structure of the program, and didn't require fumbling to get the syntax right. But from then on, it needed further prompts to give more specific results. At some point, it was better to just write the rest of the code.
  2. Limited modularity - My initial set of responses were an unwieldy wall-of-code. After a few attempts to make ChatGPT refactor it and use more functions, I ended up with a set of several functions without a main program. Ufff.
  3. No error handling - While the code provided by ChatGPT worked initially, it could not handle even the most basic errors. Based on the follow-up prompts, the code corrected itself which was nice to see. But it took a lot of wrangling to get it right while it sheepishly said, ‘I apologize for my mistake’ each time.
  4. Good explanation - ChatGPT was nice enough to explain complicated sections of the code, based on follow-up prompts. It could also provide general examples to explain certain portions of syntax or a specific method.
  5. Might repeat itself - Based on follow-up prompts, ChatGPT could customize the program. But after a few iterations, it ended up repeating a previous response. Also, specific changes included earlier were not in later versions of the code. While ChatGPT does not ‘store’ any information, I expected it would use the history of the chat to guide further responses.

It would have been nice to have ChatGPT ask follow-up questions before attempting to answer a problem.

Overall, a very fun exercise (though it took a few hours). It is very interesting what future iterations of this technology can do.

I heard that GitHub Copilot works much better as a programming assistant. If you have used it, let me know.

Dinakaran Sankaranarayanan

Software Development Manager @ Amazon | Building Digital Payment Solutions | GenAI

1 年

Interesting, beyond the hype, was curious to hear more about the practical day to day experience. Seems like tech can help really well for a limited set of common use cases, not very helpful when it comes to refinement etc. Would love to see some video of how this worked in action ??????

要查看或添加评论,请登录

Jose Simon的更多文章

  • Personal Finance Management: Goodbye Mint, Hello Lunch Money

    Personal Finance Management: Goodbye Mint, Hello Lunch Money

    On March 23rd, Intuit shut down Mint, its personal finance management product. I’d relied on Mint for over a decade for…

    8 条评论
  • Reading 'The Microstress Effect'

    Reading 'The Microstress Effect'

    Read this interesting book recently - The Microstress Effect by Rob Cross and Karen Dillon. The authors compiled this…

    4 条评论
  • ChatGPT - A Programming Tutor

    ChatGPT - A Programming Tutor

    Sal Khan (from The Khan Academy) gave a TED talk on how AI solutions (based on LLM) could improve education. He…

  • Reading 'Like, Comment, Subscribe'

    Reading 'Like, Comment, Subscribe'

    Like, Comment, Subscribe by Mark Bergen is a fascinating book about the history and rise of YouTube into the second…

    2 条评论
  • Tips for a healthy work environment?

    Tips for a healthy work environment?

    It seems the pandemic has forced a lot of people to re-evaluate their relationship with work. There are articles…

  • Reading 'The Missing Readme'

    Reading 'The Missing Readme'

    The Missing Readme is a book by Chris Riccomini and Dmitriy Ryoboy with advice for new software engineers. There is a…

    1 条评论
  • Reading 'Lights Out'

    Reading 'Lights Out'

    Lights Out: Pride, Delusion, and the Fall of General Electric by Ted Mann and Thomas Gryta is a book about GE’s…

    3 条评论
  • IronViz - A data story in 20 minutes

    IronViz - A data story in 20 minutes

    TC21 (Tableau Conference 21) with the IronViz competition wrapped up a few weeks ago. For those not familiar, IronViz…

  • Good documentation - the YouTube Data API

    Good documentation - the YouTube Data API

    Recently, I wanted to get some information about a few YouTube channels and ended up exploring the YouTube Data API. I…

    6 条评论
  • Stress in the workplace

    Stress in the workplace

    This one’s going to be brief. Two articles about the evolving workplace.

    1 条评论

社区洞察

其他会员也浏览了