Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AI assistants: The convenient crutch for new developers or a recipe for disaster

blog.codeanywhere.com

Post reply on HN
Print view View original

61–70 of 76 posts

Re: AI assistants: The convenient crutch for new developers or a recipe for disaster

#61

Post by dumpsterdiver »

brookst wrote: post #43
blackbear_ wrote: post #39

Earlier quoted context omitted.

By definition, there's never any data to judge innovations. Obviously some opinions turns out to be wrong, but if everybody just waits for data before doing anything, nothing will ever happen. So if you don't like what they are saying, at least try to provide a counterargument.

“There is no evidence supporting that argument” is a counter argument. Or maybe it’s better to say that hand-wringing is not an argument that merits a counter argument.

The difference is that one side has put actual thought into their argument, while the other side is attempting to invalidate the argument based on the fact that people other than themselves have not put in the work necessary to make a claim one way or the other.

Scientific progress doesn't happen by referencing the vast stores of data that we haven't collected.

Re: AI assistants: The convenient crutch for new developers or a recipe for disaster

#62

Post by sorokod »

brookst wrote: post #55
sorokod wrote: post #45

Earlier quoted context omitted.

Perhaps in ten years, till then I'd like software to be clearly labeled with "contains AI generated code" when that is the case.

Sure, just as soon as we get those “contains code from new college hires” label I’ve been asking for. Relying on perfect coding skills is a losing game. Way better to have healthy code review and testing processes that assume your developers are fallible.

I was writing in jest but yours is a fine label too.

Re: AI assistants: The convenient crutch for new developers or a recipe for disaster

#64

Post by 908B64B197 »

kneebonian wrote: post #32

Here's my concern with this. Is that the AI is good at generating "mostly correct" code, that will have subtle errors, so less skilled coders just take the output of whatever the LLM spits and assume it's correct, later it turns out there is a bug. The person who submitted the code doesn't understand the code, because they didn't bother learning it just that it was mostly correct. Instead of discovering and fixing th…

> so less skilled coders just take the output of whatever the LLM spits and assume it's correct, later it turns out there is a bug. The person who submitted the code doesn't understand the code, because they didn't bother learning it just that it was mostly correct. Instead of discovering and fixing the source of the error they just go in and discover where the error is output and slap some more AI generated code over it to squash the bug.

Ever worked with offshored programmers (won't name country or companies)? The things I've seen. Getting code via email that doesn't compile. Then seeing they replied-all, cc'd some random employee not on the project and 2-3 managers about "getting the urgent fix". Having a teenager with a 3 months bootcamp, an AI and a few post-it with git commands would actually be an improvement over this.

> The issue is that the biggest thing AI brings is it allows you to generate lots of code, very fast. So we have more and more code, that is less and less understood by any human being.

I know guys whose whole contracting careers is re-writing (completely from scratch) huge codebase that were offshored. 10x reduction in line count is pretty much standard. I guess these AIs means their business model will keep working for the next decade!

Re: AI assistants: The convenient crutch for new developers or a recipe for disaster

#65

Post by tuxracer »

bathtub365 wrote: post #59
leobg wrote: post #49

Earlier quoted context omitted.

So how about just prompting it with the task of not only producing the code, but also test cases to go along with it? Somebody please make a SaaS out of this idea, with a fancy tailwind sales page and a “generous free tier”. :-P

Now you have to check generated code and generated test cases for correctness, instead of just code.

yes that's true, and sincerely keep going with that maybe another pass could do code review

maybe an elaborate workflow, but each individual step in that workflow isn't insurmountable

if you cannot get the correct answer in one shot, instead a workflow is required, we should just write off this whole thing as useless or setup that workflow? will let the reader decide

Re: AI assistants: The convenient crutch for new developers or a recipe for disaster

#66

Post by burnished »

nkko wrote: post #50
burnished wrote: post #36

Was this article AI written? This is exactly the same format of argument that convinced me as a learner to use notepad++ for years, which I now believe to be a garbage idea. IDEs provide so much important contextual information - a copilot program to show you different techniques would be helpful in a similar vein. Caveat: chatGPT is a chat program, that it can produce working code in places is a coincidence, it woul…

We are trying to build a workflow and it goes like this: - we sketch the general idea for the article in Notion - we use ChatGPT to expand on the topic and explore contrarian perspectives to validate the idea - I do the final edit and use Grammarly and Quilbot to ensure clarity and fluency - result goes onto our 400k subs newsletter (from a 1mil list of our users who opened any of our newsletters at least once) - fee…

Let me give you some direct feedback on this then - it reads as 'content' and not an article. ChatGPT seems to blow out word count in a fluent way but the resultant text seems to have much lower information density, the sort of thing you might expect from a student learning to write paragraphs. Genuinely I asked if it was AI generated because it felt like filler.

Perhaps you need an editing down phase?

Re: AI assistants: The convenient crutch for new developers or a recipe for disaster

#67

Post by jmnicolas »

kneebonian wrote: post #32

Here's my concern with this. Is that the AI is good at generating "mostly correct" code, that will have subtle errors, so less skilled coders just take the output of whatever the LLM spits and assume it's correct, later it turns out there is a bug. The person who submitted the code doesn't understand the code, because they didn't bother learning it just that it was mostly correct. Instead of discovering and fixing th…

Here is an anecdote to illustrate how "The Machine TM" tried to get me fired.

For context, Microsoft introduced a "AI revamped Intellisense" in Visual Studio (not Code) a few months ago. It's not Copilot, it just makes suggestions but only for your next line of code. It's Okish most of the suggestions are good, it saves time on repetitive tasks.

Yesterday I was writing some code to disable some customers. I had a list of all customers and a list of customers to disable. Intellisense offered to pass the list of all customers to the method that will disable them. If I wasn't paying attention, next Monday (and the rest of the week really) would have been quite "entertaining".

Re: AI assistants: The convenient crutch for new developers or a recipe for disaster

#68

Post by jmnicolas »

antonvs wrote: post #46
kneebonian wrote: post #32

Here's my concern with this. Is that the AI is good at generating "mostly correct" code, that will have subtle errors, so less skilled coders just take the output of whatever the LLM spits and assume it's correct, later it turns out there is a bug. The person who submitted the code doesn't understand the code, because they didn't bother learning it just that it was mostly correct. Instead of discovering and fixing th…

What you're describing will primarily happen at incompetent orgs without good development practices, code review, good management, good hiring, etc. If anything, a tool that reveals and punishes incompetence is good for everyone. I'm not the world's most enthusiastic capitalist, but in this case, I think we can let the market sort it out.

Good for you that you can choose only the best.

The rest of us are in the trenches making do despite the unending stream of spaghetti code that cruel gods have chosen to torment us with.

Re: AI assistants: The convenient crutch for new developers or a recipe for disaster

#69

Post by brookst »

dumpsterdiver wrote: post #61
brookst wrote: post #43

Earlier quoted context omitted.

“There is no evidence supporting that argument” is a counter argument. Or maybe it’s better to say that hand-wringing is not an argument that merits a counter argument.

The difference is that one side has put actual thought into their argument, while the other side is attempting to invalidate the argument based on the fact that people other than themselves have not put in the work necessary to make a claim one way or the other. Scientific progress doesn't happen by referencing the vast stores of data that we haven't collected.

Thought != data

Re: AI assistants: The convenient crutch for new developers or a recipe for disaster

#70

Post by mellavora »

anigbrowl wrote: post #38

I think there's a secret third thing, domain specific fundamentals/boilerplate. I've had good results with code generation for minimal proof-of concept things, like 'show me code for [maze construction algorithm]' or 'visualize this platonic solid in mathplotlib, with numeric labels on every vertex' or 'fetch data from https://hacker-news.firebaseio.com/v0/item/34741898.json and build a pandas dataframe from it'. I'v…

> I've come to prefer it to visiting Stack Overflow when I need to get up to speed on a new thing,

I'm certainly guilty of this very same mistake, key word being "mistake." I'd hope for a world where the better way would be to read some good docs which gave an accurate mental model of the thing I want to get up to speed with. You know, organized and structured knowledge.

vs a quick answer to a single point without any context.

Post reply on HN