I dont use ai code generation tools, I just use claude as a search engine. It hasn't changed the output rate of my code but I believe that its improved the quality of it by exposing me to patterns and features that I otherwise may not have. I used to take a very object oriented approach to code, but when I would ask claude to look at my code and critique it, it would often lead me into more functional patterns, with result type returns and eliminating global state. Ive completely stopped using exceptions and functional programming has GREATLY increased the confidence I have in my code to the point where I write 2000 lines at a time and get a successful first test nearly every time.
The credit lies with a more functional style of C++ and typescript (the languages i use for hobbies and work, respectively), but claude has sort of taken me out of the bubble I was brought up in and introduced new ideas to me.
However, I've also noticed that LLM products also tend to reinforce your biases. If you dont ask it to critique you or push back, it often tells you what a great job you did and how incredible your code is. You see this with people who have gotten into a kind of psychotic feedback loop with ChatGPT and who now believe they can escape the matrix.
I think LLMs are powerful, but only for a handful of use cases. I think the majority of what theyre marketed for right now is techno-solutionism and theres an impending collapse in VC funding for companies that are plugging in chatgpt APIs for everything from insurance claims to medical advice
Then unfortunately you're leaving yourself at a serious disadvantage.
Good for you if you're able to live without a calculator, but frankly the automated tool is faster and leaves you less exhausted so you should be taking advantage of it.
That's a very narrow perspective.
Will the tool deskill me? Will the tool lower my work quality? Will the tool make a bigger share of my work reviewing vs thinking and creating? Will the tool make the work overall less interesting (which motivates me)? Etc. Etc.
This is even assuming that the FOMO is justified. So fat studies don't show this is the case, but things might change.
They are using them, just in a curated and deliberate way.
I use it similar to the parent poster when I am working with an unfamiliar API, in that I will ask for simple examples of functionality that I can easily verify are correct and then build upon them quickly.
Also, let me know when your calculator regularly hallucinates. I find it exhausting to have an LLM dump out a "finished" implementation and have to spend more time reviewing it than it would take to complete it myself from scratch.
Writing code is the only part of my job that I like. Im not exhausted by coding because I love coding. Im exhausted by pointless meetings, talking to clients, and trying to bring non technical people up to speed with what im working on. Allowing a machine to write code for me and then manually editing it sounds like a really really miserable way to spend the precious little time I have on this earth
Is typing speed a bottle neck for people? Because otherwise you’re offloading thinking to the LLM. Unless you can understand code faster than you can write it (which I’ve never experienced - best case scenario I can understand as fast as I read).
As a junior I used to think it was ok to spend much less time on the review than the writing, but unless the author has diligently detailed their entire process a good review often takes nearly as long. And unsurprisingly enough working with an AI effectively requires that detail in a format the AI can understand (which often takes longer than just doing it).
Yes, if it isn't your being overpaid in the view of a lot of people. Step out of the way and let an expert use the keyboard.
How can you not read and understand code but spend time writing it? That's bad code in that situation.
Source: try working with assembly and binary objects only which really do require working out what's going on. Code is meant to be human readable remember...
The credit lies with a more functional style of C++ and typescript (the languages i use for hobbies and work, respectively), but claude has sort of taken me out of the bubble I was brought up in and introduced new ideas to me.
However, I've also noticed that LLM products also tend to reinforce your biases. If you dont ask it to critique you or push back, it often tells you what a great job you did and how incredible your code is. You see this with people who have gotten into a kind of psychotic feedback loop with ChatGPT and who now believe they can escape the matrix.
I think LLMs are powerful, but only for a handful of use cases. I think the majority of what theyre marketed for right now is techno-solutionism and theres an impending collapse in VC funding for companies that are plugging in chatgpt APIs for everything from insurance claims to medical advice