Another great example, is the power of tabbing with Cursor. If I want to change the parameters of a function in my React app, I can be at one of the functions anywhere in my screen, add a variable that relates to what is being rendered, and I can now quickly tab through to find all the spots that also are affected in that screen, and then it usually helps apply the changes to the function. It's like smart search and replace where I can see every change that needs made but it knows how to make it more intelligently than just replacing a line of code - and I didn't have to write the regex to find it, AND it usually helps get the work done in the function as well to reflect the change. That could save me 3-5 minutes, and I could do that 5 times a day maybe, and another almost half-hour is saved.
The point is, these small things add up SO fast. Now I'm incredibly efficient because the tedious part of programming has been sped up so much.
How much do you believe a programmer needs to layout to “get good”?
I think that getting "good" at using AI means that you figure out exactly how to formulate your prompts so that the results are what you are looking for given your code base. It also means knowing when to start new chats, and when to have it focus on very specific pieces of code, and finally, knowing what it's really bad at doing.
For example, if I need to have it take a list of 20 fields and create the HTML view for the form, it can do it in a few seconds, and I know to tell it, for example, to use Bootstrap, Bootstrap icons, Bootstrap modals, responsive rows and columns, and I may want certain fields aligned certain ways, buttons in certain places for later, etc, and then I have a form - and just saved myself probably 30 minutes of typing it out and testing the alignment etc. If I do things like this 8 times a day, that's 4 hours of saved time, which is game changing for me.
I've probably fed $100 in API tokens into the OpenAI and Anthropic consoles over the last two years or so.
I was subscribed to Cursor for a while too, though I'm kinda souring on it and looking at other options.
At one point I had a ChatGPT pro sub, I have found Claude more valuable lately. Same goes for Gemini, I think it's pretty good but I haven't felt compelled to pay for it.
I guess my overall point is you don't have to break the bank to try this stuff out. Shell out the $20 for a month, cancel immediately, and if you miss it when it expires, resub. $20 is frankly a very low bar to clear - if it's making me even 1% more productive, $20 is an easy win.
Also, the auto-complete with tools like Cursor are mind blowing. When I can press tab to have it finish the next 4 lines of a prepared statement, or it just knows the next 5 variables I need to define because I just set up a function that will use them.... that's a huge time saver when you add it all up.
My policy is simple, don't put anything AI creates into production if you don't understand what it's doing. Essentially, I use it for speed and efficiency, not to fill in where I don't know at all what I'm doing.