AI’s not bad, it just doesn’t save me time. For quick, simple things, I can do it myself faster than the AI. For more big, complex tasks, I find myself rigorously checking the AI’s code to make sure no new bugs or vulnerabilities are introduced. Instead of reviewing that code, I’d rather just write it myself and have the confidence that there are no glaring issues. Beyond more intelligent autocomplete, I don’t really have much of a need for AI when I program.
This is how I use it, and it's a great way for me to speed up. It's a rubber duck for me. I have a fake conversation, it gives me different ideas or approaches to solve a problem. It does amazing with that
The code it spits out is something else though. The code it's trained on in GitHub means it could be based on someone with 2 months experience writing their CS201 program, or a seasoned experienced engineer. I've found it faster to get the gist of what it's saying, then rewrite it to fit my application.
Not even mentioning the about 50% chance response of "hey why don't you use this miracle function that does exactly what you need" and then you realize that the miracle function doesn't exist, and it just made it up.
I use it a lot for writing documentation comments (my company's style guide requires them), and for small sections at a time. Never a full solution.
AI’s not bad, it just doesn’t save me time. For quick, simple things, I can do it myself faster than the AI. For more big, complex tasks, I find myself rigorously checking the AI’s code to make sure no new bugs or vulnerabilities are introduced. Instead of reviewing that code, I’d rather just write it myself and have the confidence that there are no glaring issues. Beyond more intelligent autocomplete, I don’t really have much of a need for AI when I program.
This is how I use it, and it's a great way for me to speed up. It's a rubber duck for me. I have a fake conversation, it gives me different ideas or approaches to solve a problem. It does amazing with that
The code it spits out is something else though. The code it's trained on in GitHub means it could be based on someone with 2 months experience writing their CS201 program, or a seasoned experienced engineer. I've found it faster to get the gist of what it's saying, then rewrite it to fit my application.
Not even mentioning the about 50% chance response of "hey why don't you use this miracle function that does exactly what you need" and then you realize that the miracle function doesn't exist, and it just made it up.
I use it a lot for writing documentation comments (my company's style guide requires them), and for small sections at a time. Never a full solution.