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

91–100 of 526 posts

Re: A ChatGPT mistake cost us $10k

#91

Post by viraptor »

brigadier132 wrote: post #81
viraptor wrote: post #28

Earlier quoted context omitted.

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…

> db wiped for good isolation Why? In fact, not having good isolation would have caught this bug. Generate random emails for each test. Why would you test on a completely new db as if that is what will happen in the real world?

It's extremely common. You want to know that objects/rows from one test don't bleed into another by accident. It allows you to write more strict and simpler assetions - like "there's one active user in the database" after a few changes, rather than "this specific user is in the database and active and those other ones are not anymore".

Leaking information between test runs can actually make things pass by accident.

Re: A ChatGPT mistake cost us $10k

#92

Post by moody__ »

fzeroracer wrote: post #58
morgante wrote: post #8

Earlier quoted context omitted.

Honestly I'm not sure why ChatGPT has anything to do with this problem. I remember making the exact same mistake (accidentally using a single function call in a schema) back in 2010. No LLMs required. The bigger culprit is probably a lack of testing / debugging. This error would immediately get caught if you simply registered twice on a test instance.

In a world where this entire codebase wasn't generated by ChatGPT, you'd have engineers familiar with the various parts of the system to quickly identify and fix the problem. Testing and debugging isn't just a matter of stepping through code, it's an exercise of seeing where your mental model of the codebase is faulty versus the current reality of it. I've encountered similar problems and they'd be fixed in a matter…

This is spot on, the issue is not the mistake per se but in creating a code base that the team themselves are not familiar with. With some intern or team member generated code you can sit down with them and have them walk you through the code and introduce you to their reasoning, but you can't do that with an LLM. The author even admits to just mimicking the existing structure that the LLM started with when they had to expand, which sounds like a first commit for a team member first getting familiar with some new code. Part of the benefit of being able to write your own code is that you can do it in a way that clicks for you. Hopefully this lets you debug and extend it efficiently. I don't know why someone would squander this opportunity.

Re: A ChatGPT mistake cost us $10k

#93

Post by bluelightning2k »

It is strange that this took 5 days to find. Simply because of logs.

Go to logs. Filter by errors. Oh, errors in insert subscription. Seems relevant.

I could understand if the errors were somewhere else.

Even if logs didn't exist. Problematic endpoint generating 50 emails per day? I would have immediately thrown a try catch and rendered the error to the user if logging was impossible. Then your very next bug report solves it.

Assuming that they had the error (guid collision) - it's not as easy to spot as some commentators are making out. But surely after reading the code s few times.

Ironically they should have asked ChatGPT for help debugging

Re: A ChatGPT mistake cost us $10k

#94

Post by nicce »

__jonas wrote: post #83
nicce wrote: post #55

Earlier quoted context omitted.

> NextJS There is well-hidden vendor-lock when using NextJS, at least.

that’s a bold claim, could you give an example?

Probably the most known example https://github.com/vercel/next.js/discussions/19065

It is not an issue if you host in Vercel.

Implementing the requested feature would make the framework much better and easier to use when self-hosted elsewhere. But there is neglection to resolve the issue. This is just one case.

Re: A ChatGPT mistake cost us $10k

#95

Post by bluepnume »

tazjin wrote: post #76
viraptor wrote: post #54

Earlier quoted context omitted.

This code would pass static type validation, there's nothing wrong with it at that level. It gets a default value to use and does exactly that.

Sure, you can follow along the old meme: https://twitter.com/vbhvsgr/status/1419369352164372482 Though in practice in decent languages it's much less likely you'd write your own `any -> any, any`-typed library for whatever (in this case DB interactions), and use a strongly typed one in which this would at least have been a much more explicit mistake to make.

But this isn't an `any -> any` case. They passed in a default value, as a string, which is the correct type for a default value for this column. Even with very strong typing they wouldn't have got a type error here right?

Re: A ChatGPT mistake cost us $10k

#97

Post by mattigames »

nicce wrote: post #86
brigadier132 wrote: post #78

Earlier quoted context omitted.

There is no vendor lockin with nextjs

Simply put - if you want get the best out of the framework, you need to host it in Vercel. Otherwise, there are better options for frameworks. No need to ”fight it”. You will find many issues from GitHub which are not considered because they would make the framework ”better” or easier to use on other clouds.

Making things worse in a free offering by a company to profit from premium offerings by the same company its the pinacle of capitalism, reminds me of a recurrent joke I have with a friend while playing Call Of Duty, that they will get greedier and soon will sell not only character's skins but also shaders/textures for the maps, oh so you want to see something better than placeholder textures? We have the DLC just for you!

Re: A ChatGPT mistake cost us $10k

#98

Post by mvdtnz »

Everyone focusing, understandably, on the poor coding and testing practices. But this kind of thing blows my mind,

> This problem became really well hidden because of our backend setup. We had eight ECS tasks on AWS, all running five instances of our backend (overkill, yes we know, but to be fair we had AWS credits).

I mean sure, you acknowledge that it's overkill, but my word is that OVERKILL. You're servicing customers numbering in the double digits and you're using more cloud resources than could run entire established businesses. I feel like a lot of developers today have totally lost sight of what computers are capable of, and just over-provision (and overcomplicate) as a default approach. This is scary.

Re: A ChatGPT mistake cost us $10k

#99

Post by Terretta »

userbinator wrote: post #21
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.

> It read like no one really knew what they were doing. "We just let [devs] generate the code and everything seemed to work" is certainly not a good way to [whatever].

Except, have you met startup devs? This is by and large the "move fast then unbreak things" approach.

Re: A ChatGPT mistake cost us $10k

#100

Post by elforce002 »

Thanks for sharing. Where I work we know chatGPT exists but we're still using SO for obscure errors. We don't trust any copilot when dealing with our livelihoods.

At least you got away "easy". I'm waiting for the "...cost us $100k..." post.

Post reply on HN