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

I'm tired of fixing customers' AI generated code

medium.com

Post reply on HN
Print view View original

101–110 of 345 posts

Re: I'm tired of fixing customers' AI generated code

#101

Post by PeterStuer »

gorbachev wrote: post #96

I've been saying for a while now that there's an absolute gold mine waiting for people who want to specialize in fixing AI generated applications. A lot of businesses are going to either think they can have generative AI create all of their apps with the help of a cousin of the wife of the accountant, or they unknowingly contract a 10x developer from Upwork or alike who uses generative AI to create everything. Once t…

Doesn't solve the problem that the budget they has in mind for the app was $300, while an experienced dev can directly see this is going to be a $20K v.1 before change requests project.

Re: I'm tired of fixing customers' AI generated code

#102

Post by fragmede »

FanaHOVA wrote: post #83
alexeiz wrote: post #55

I had a related episode at work when my coworker asked me why his seemingly trivial 10 line piece of code was misbehaving inexplicably. It turned out he had two variables `file_name` and `filename` and used one in place of another. I asked him how he ended up with such code, he said he used copilot to create it. Using code from a generative AI without understanding what it does is never a good idea.

Copilot wouldn't make a typo. He just made that up and / or broke the code himself.

would someone invent that and bother the author with that? I mean I suppose it's possible, but that seems like such a waste of time to me that I find that more unlikely. and while it's a typo, it's not fleinaem or something that's totally wrong, just a choice in breaking up the word filename. having written file handling code, the various permutations of filename and path and dirname get to be a bit much sometimes.

Re: I'm tired of fixing customers' AI generated code

#103

Post by hinkley »

wuming2 wrote: post #44
mrbombastic wrote: post #17

Earlier quoted context omitted.

A week is not anywhere close to enough to learn programming in any meaningful way for someone with no experience.

Time to expertise is down to zero in “Fake until you make it” circles. 260 week-long iterations later, having survived the “hype curve” and the “Valley of Death”, they declare themselves “battle-proven”. A.k.a. experts.

Expert beginners.

Re: I'm tired of fixing customers' AI generated code

#105

Post by nope1000 »

FanaHOVA wrote: post #83
alexeiz wrote: post #55

I had a related episode at work when my coworker asked me why his seemingly trivial 10 line piece of code was misbehaving inexplicably. It turned out he had two variables `file_name` and `filename` and used one in place of another. I asked him how he ended up with such code, he said he used copilot to create it. Using code from a generative AI without understanding what it does is never a good idea.

Copilot wouldn't make a typo. He just made that up and / or broke the code himself.

I don't know about copilot but I've seen typos from ChatGPT (although it was english, not code)

Re: I'm tired of fixing customers' AI generated code

#106

Post by fragmede »

FeepingCreature wrote: post #98
stitched2gethr wrote: post #51

Earlier quoted context omitted.

I'm a bit torn. My first thought was "If the current state of the art LLMs made the mistakes it's unlikely an LLM would be able to correct them." But I'm not sure that's true if the support LLM (chat bot) is given very specific instructions so as to limit the possible answers. Still I think that's gonna break down pretty quick for other reasons. Maybe the chat bot can recognize a botched request and even suggest a fi…

> I'm a bit torn. My first thought was "If the current state of the art LLMs made the mistakes it's unlikely an LLM would be able to correct them." But, I mean, that doesn't make sense even for humans, right? 99% of the errors I make, I can easily correct myself because they're trivial. But you still have to go through the process of fixing them, it doesn't happen on its own. Like, for instance, just now I typoed "st…

The first time I asked ChatGPT to write a function, have it run it and repeat until the function meets given test cases, in one shot, was pretty cool.

Re: I'm tired of fixing customers' AI generated code

#107

Post by creesch »

FanaHOVA wrote: post #100
creesch wrote: post #92

Earlier quoted context omitted.

LOL, are you kidding me? LLMs including the gpt family copilot uses are very good at sneaking in these sorts of thing.

Show me 1 example.

Show me that copilot never makes a mistake or introduces variables that never have been initialized...

Re: I'm tired of fixing customers' AI generated code

#108

Post by KoolKat23 »

PeterStuer wrote: post #101
gorbachev wrote: post #96

I've been saying for a while now that there's an absolute gold mine waiting for people who want to specialize in fixing AI generated applications. A lot of businesses are going to either think they can have generative AI create all of their apps with the help of a cousin of the wife of the accountant, or they unknowingly contract a 10x developer from Upwork or alike who uses generative AI to create everything. Once t…

Doesn't solve the problem that the budget they has in mind for the app was $300, while an experienced dev can directly see this is going to be a $20K v.1 before change requests project.

And this is why people continue to do it. And at that, with such a discrepancy, why not? Proof of concept, you know if it adds value and makes money, enough money to pay $20k.

Re: I'm tired of fixing customers' AI generated code

#109

Post by brigadier132 »

FanaHOVA wrote: post #83
alexeiz wrote: post #55

I had a related episode at work when my coworker asked me why his seemingly trivial 10 line piece of code was misbehaving inexplicably. It turned out he had two variables `file_name` and `filename` and used one in place of another. I asked him how he ended up with such code, he said he used copilot to create it. Using code from a generative AI without understanding what it does is never a good idea.

Copilot wouldn't make a typo. He just made that up and / or broke the code himself.

You are getting downvoted but you are right, a typo in a variable that already exists in a file like this is not the failure mode for LLMs. The failure mode is logic bugs, making up methods / functions.

Re: I'm tired of fixing customers' AI generated code

#110

Post by randomdata »

core_dumped wrote: post #15
OutOfHere wrote: post #7

[flagged]

Language models aren’t AI no matter how hard you squint. When we get actual AI (not counting on anytime soon) it will be more than the annoyed developer that loses their job

> Language models aren’t AI no matter how hard you squint.

While you are free to make up any definition you want on the spot, so are others. Yes, language models are just plain old boring machine learning like any other, but machine learning is a subset of what most people consider to be the area of AI.

> When we get actual AI (not counting on anytime soon) it will be more than the annoyed developer that loses their job

Again, while you can define things however you please, so can everyone else. This is what most people would consider AGI, not AI.

Post reply on HN