Ever since the release of Github copilot, and especially the massive popularity of chatGPT, AI tools can be used to generate code based on prompting or on the fly suggestions in your IDE. There are concerns regarding the data you share while using these, especially when used in a work environment, but there is another big reason why I'm personally not keen to adopt these kind of tools. The risk of of sabotaging my own development. Hear me out.
As a developer, you can use all the tools you want provided that they confirm to your company's policies. At least you should be, developer freedom matters. You are however, in the end, solely responsible for the work you deliver. You cannot blame the tools you used if you copied a piece of code, whether from ChatGPT or one of the older go-tos like StackOverflow.
Life long learning
Our capabilities are ever changing. We learn new things every day, but knowledge, if not refreshed, also fades and some knowledge simply becomes outdated. This is especially true in the rapidly evolving field of IT. Thus is important to not just deliver the work we need to deliver, but also use that time effectively to build long-lasting knowledge.
The conclusion from this is that we should try to incorporate principles of effective learning on the job. I've read some interesting material on this in the past, which i wholeheartedly recommend 1.
How not to use ChatGPT
As coders, we use our toolbox of language features, design patterns and so on to solve new problems. Coming up with a solution should require effort, it should require us to dig into our existing knowledge and try to make new connections. This process of trial and error is an effective tool of learning. On the other hand, generating code with ChatGPT, copying it and then trying to understand it skips this process entirely. It requires less effort, but also gives less long-term gains. Over time, i believe this approach would be a detriment to my coding abilities. It is these same coding abilities that we need to analyse the code generated by ChatGPT.
Not all is bad
Much like linters, AI generated code reviews may help you to spot mistakes and improvements. The Key thing is these happen after you've made the effort to write the code. Getting feedback after making the effort is very valuable. The process of trial and error requires knowing that you've made a mistake to then learn from it, otherwise it would just be trail and ignorance. While the AI review may contain mistakes, it will help you reflect on your work and consider alternatives.
Final thoughts
I'm sure there are many more ways of how not to use or not to use tools like ChatGPT for work other than the two i've just mentioned. The most important question i ask myself is whether it reduces mental effort. Seeing as effort is an important indicator of creating lasting knowledge, this is something i want to avoid.
-
Brown, P. C. (2014). Make it stick. Belknap Press. ↩
Top comments (0)