Hacker News Reader

Comment by sidlls | Hacker News Reader

The response time is longer than it would have taken you to just write the code.

Even writing the statement in natural language takes longer than writing the code...

the point is not the speed, but the brainspace. the brainspace I would have used on this task would have tired me out quicker and prevented me from making progress on other tasks.

ChatGPT is literally 0 brain space for these simple tasks. If you had to code it you're at least thinking about edge cases etc. Plus there's 0% chance it would take you 20 seconds for 10+ tasks of these per day. if you're coding at 50 wmp these would take you at least 1 minute to type out, let alone implement correctly.

by your logic you should never use google or SO because it's quicker to just implement it instead of opening a browser, typing the question, looking at responses etc.

Iteration over an array is literally trivial and takes next to no time as long as one is familiar with the language constructs required. It should take about as much brain space as single digit addition: sure one could use a calculator, but he shouldn’t have to and going for it is a waste of time.

If I caught one of the other engineers on my team wasting time on google or SO looking up such basic stuff I’d question his career choice.

i'm not asking how to do a for loop lol the queries are more complex, I was just providing an example for this thread since many of you are struggling to understand why chatgpt is useful.

you seem to have an emotional reaction against chatgpt, or are just really dense. that's okay for you. but I hope your team knows that you're limiting their career growth by having you as a manager.

The examples you gave were ones you said you used specifically: iteration over an array and filtering being two. These are trivial tasks that you, as a programmer, shouldn’t need to search for in your day-to-day. This isn’t an emotional response to chatgpt, it’s questioning the abilities of anyone who would try to use it for the trivial tasks you put it to use for. I don’t know that I could trust code you submit in a PR: I sense I’d have to give it extra scrutiny, the same way I would the code produced by the AI itself.

> If you had to code it you're at least thinking about edge cases etc.

If you didn't code it you REALLY need to be thinking about edge cases, etc. ChatGPT (or stack overflow for that matter) makes tons of mistakes, at least as much as your average human.

Personally I find it harder to validate the behavior of code I didn't write than code I've gone through the creation process of myself.

It's good to employ TDD for this. Write a test and then ask ChatGPT for a solution. If it fails the test tell it and it will come up with fixes.

Sometimes it is not perfect and a couple of times I had a case where ChatGPT couldn't code something and it would go into a loop coming back to the permutation of wrong answer over and over. Most of the time starting over with different prompt describing the same task in a different way fixes it.

Reply on news.ycombinator.com