A ChatGPT mistake cost us $10k

Post by brigadier132 » Mon, Jun 10, 2024, 3:45 PM UTC

viraptor wrote: post #275

brigadier132 wrote: post #187

Earlier quoted context omitted.

Of course your tests shouldn't be sensitive to external state. Why would other tests running affect your test?

They shouldn't. But they do. We're not perfectly spherical developers and we all make mistakes. Sometimes it's also extremely tricky to figure out what state is leaking, especially is it's an access race issue and happens only for some tests and very rarely. If you haven't seen that happening, you just need to work on larger projects.

Post by spencerchubb » Mon, Jun 10, 2024, 4:04 PM UTC

paul7986 wrote: post #341

spencerchubb wrote: post #330

Earlier quoted context omitted.

That is indeed a weakness of chatgpt - it's not so good with super current information That is because it is only trained on info up to a certain date It's good to know what tools are good and bad at

ummm chatGPT is very slowly becoming mainstream... for to become fully such no user and or prospective user cares about it's limitations .. it needs to work like previous similar technologies do like Siri and Alexa. User experience is utmost important without it Apple wouldnt be apple and chatGPT as it's current trajectory is going looks to become as big as the current biggies. Thus everyone including parents/grandpa…

Post by chrisjj » Mon, Jun 10, 2024, 4:11 PM UTC

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…

Post by chrisjj » Mon, Jun 10, 2024, 4:49 PM UTC

Closi wrote: post #20

chrisjj wrote: post #2

Thanks for telling. Bookmarked for the next time we're told ChatGPT's code error rate is acceptable because we review its code just like an intern's.

Your take-away is that this is ChatGPT's fault rather than a failure of testing?

Post by lionkor » Mon, Jun 10, 2024, 5:11 PM UTC

wavemode wrote: post #65

No, a lack of monitoring cost you $10K. Your app was throwing a database exception and nobody was alerted that this was not only happening, but happening continuously and in large volumes. Such an alert would have made this a 5-minute investigation rather than 5 days. If you haven't fixed that alerting deficiency, then you haven't really fixed anything.