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

A ChatGPT mistake cost us $10k

asim.bearblog.dev

Post reply on HN
Print view View original

21–30 of 526 posts

Re: A ChatGPT mistake cost us $10k

#21

Post by userbinator »

Aurornis wrote: post #5

On one hand, thanks for being honest about a story of how this bug came to be. On the other hand, I don’t think advertising the fact that the company introduced a major bug from copy and pasting ChatGPT code around and that they spent a week being unable to even debug why it was failing. I don’t know much about this startup, but this blog post had the opposite effect of all of the other high quality post-mortem posts…

It read like no one really knew what they were doing. "We just let it generate the code and everything seemed to work" is certainly not a good way to market your company.

Re: A ChatGPT mistake cost us $10k

#23

Post by nxobject »

Aurornis wrote: post #5

On one hand, thanks for being honest about a story of how this bug came to be. On the other hand, I don’t think advertising the fact that the company introduced a major bug from copy and pasting ChatGPT code around and that they spent a week being unable to even debug why it was failing. I don’t know much about this startup, but this blog post had the opposite effect of all of the other high quality post-mortem posts…

In a way, it does give you an opportunity to think about what you appreciate in a detailed postmortem - not just a single cause, but human and organizational factors too, and an attempt to figure out explicit mitigations. I’ll admit the informality and the breezy tone here made me go “woah, they’re a bit cavalier…”

Re: A ChatGPT mistake cost us $10k

#24

Post by gwill »

DataDive wrote: post #9

proper title: database modeling bug costs company 10K but then perhaps coding the entire thing with ChatGPT saved the company more than 10K, so they came out well ahead or maybe tons of other bugs lurk that will cost the company well over 10K over the long run

either way it sounds like they're stuck with poor testing around their code. that shows the devs probably don't understand the code which means fixing or changing things in the future will take longer.

Re: A ChatGPT mistake cost us $10k

#26

Post by asddubs »

IshKebab wrote: post #16

More like how switching to Python (and not meeting Python's high testing requirements) cost you $10k. This is a well known Python foot-gun and a developer could easily have made that mistake too.

agreed, though if a developer had manually made the mistake they might have realized the problem in less than 5 days. copy paste a bunch of ai generated code into your project and no one can try to deduce where the problem might lie once something goes wrong

though a little logging would also have gone a long way. I don't really get how this could have taken 5 days to find, since they knew exactly where the problem was

Re: A ChatGPT mistake cost us $10k

#27

Post by drexlspivey »

cmeacham98 wrote: post #15

I understand how the mistake was made, it seems relatively easy to slip by even when writing code without ChatGPT. But what I don't understand is how this wasn't caught after the first failure? Does this company not have any logging? Shouldn't the fact the backend is attempting to reuse UUIDs be immediately obvious from observing the error?

Five days to figure out this bug is pretty crazy ngl

Re: A ChatGPT mistake cost us $10k

#28

Post by viraptor »

Aurornis wrote: post #5

On one hand, thanks for being honest about a story of how this bug came to be. On the other hand, I don’t think advertising the fact that the company introduced a major bug from copy and pasting ChatGPT code around and that they spent a week being unable to even debug why it was failing. I don’t know much about this startup, but this blog post had the opposite effect of all of the other high quality post-mortem posts…

They spent 5 days. The bug type is pretty common and could easily be done by a developer. (It's a similar class to the singleton default argument issue that many people complain about) Meh, I don't mind the cautionary tale and don't think chatgpt was even relevant.

It's actually a tricky bug, because usual tests wouldn't catch it (db wiped for good isolation) and many ways of manual testing would restart the service (and reset the value) on any change and prevent you from seeing it. Ideally there would be a lint that catches this situation for you.

Re: A ChatGPT mistake cost us $10k

#29

Post by hipadev23 »

This is a great example of why SQLAlchemy is a terrible ORM, and chatGPT is not alone in making the same mistake as millions of engineers, in fact likely where it learned the mistake.

default = python code evaluates the default value as necessary for each new record

server_default = the initial CREATE TABLE uses this computed (from python) value, thus the hardcoded UUID. They also could have done server_default=text("uuid_generate_v4()") if they had that corresponding module installed on postgres.

Post reply on HN