TL;DR Don’t install Copilot. It rots your brain and destroys the environment.

A rubber duck in use by a developer to aid code review

GitHub Copilot is a technology that is designed to help you write code, kind of like your partner in pair programming. But, you know, it’s not an actual person. It’s “A.I.”–whatever that means.

In principle this sounds like it might actually be a good thing right? I know several people, who I respect, that use it as part of their daily work. I’ve heard smart people say AI coding assistants like Copilot will democratize programming, by making it possible for more people to write code, and automate the drudgery out of their lives. I’m not convinced.

Here’s why I don’t use Copilot (or ChatGPT) to write code:

  1. Copilot’s suggestions are based on a corpus of open source code in GitHub, but the suggestions do not mention where the code came from, and what the license is. GitHub is stealing and selling intellectual property.
  2. Copilot lets you write code faster. I don’t think more code is a good thing. The more code there is, the more code there is to maintain. Minimalism in features is usually a good thing too. Less really is more.
  3. As more and more programmers use Copilot it creates conservativism in languages and frameworks that prevents people from creating and learning new ways of doing things. Collectively, we get even more stuck in our ways and biases. Some of the biases encoded into LLMs are things that we are actively trying to change.
  4. Developers become dependent on Copilot for intellectual work. Actually, maybe addicted is a better word here. The same could be (and was) said about the effect of search engines on software development work (e.g. Googling error messages). But the difference is that search results need to be interpreted, and the resulting web pages have important context that you often need to understand. This is work that Copilot optimizes away and truncates our knowledge in the process.
  5. Copilot costs money. It doesn’t cost tons of money (for a professional person in the USA) but it could be significant for some. Who does it privilege? Also, it could change (see point 4). Remember who owns this thing.
  6. How much energy does it take to run Copilot as millions of developers outsource their intellectual work to its LLM infrastructure? Is this massive centralization and enclosure really progress in computing? Or is it a step backwards as we try to reduce our energy use as a species?
  7. What does Copilot see of the code in your editor? Does it use your code as context for the prompt? What does it store, and remember, and give to others? Somebody has probably looked into this, but if they have it is always up for revision. Just out of principle I don’t want my editor sending my code somewhere else without me intentionally doing it.
  8. Working with others who use Copilot makes my job harder, since they sometimes don’t really understand the details of why the code is written a particular way. Over time Copilot code can mix idioms, styles and approaches, in ways that the developer doesn’t really understand or even recognize. This makes maintenance harder.

As far as I can tell the only redeeming qualities of Copilot are:

  1. Copilot encourages you to articulate and describe a problem as written prose before starting to write code. You don’t need Copilot for this. Maybe keep a work journal or write a design document? Maybe use your issue tracker? Use text to communicate with other people.
  2. Copilot is more interactive than a rubber duck. But, it turns out Actual People are even more interactive and surprising. Reach out to other professionals and make some friends. Go to workshops and conferences.
  3. I could be convinced that Copilot has a useful place in the review of code rather than the first draft of code. It wouldn’t be a replacement for review by people, but I believe it could potentially help people do the review. I don’t think this exists yet?
  4. Copilot makes me think critically about machine learning technology, my profession and its place in the world.

Maybe my thinking on this will change. But I doubt it. I’m on the older side for a software developer, and (hopefully) will retire some day. Maybe people like me are on the way out, and writing code with Copilot and ChatGPT is the future. Maybe programming has always been about increasing layers of abstraction and this is just the next logical layer. I really hope not.

I enjoy programming because it’s about reasoning, thinking, models, concepts, expression, communication, ethics, reading, learning, making, and process. It’s an art and a practice that is best done with other people.

Increasingly I think it’s imperative for programming to be done more slowly, more deliberatively, and as part of more conversations with more people. The furious automation of everything is eating the world.

Programs need to run more efficiently. Programs need to be well understood, by a more diverse and varied set of people. Programs need to be robust and resilient. Programs need to be easier to change.

Can Copilot help with these goals? I think the answer is no, because it doesn’t actually understand anything, and more importantly, it doesn’t promote understanding.

Update (2023-06-09): For another take on Copilot that uses this post as a jumping off point see Vivek Haldar’s Re: Why I don’t use Copilot.