Almost a tautological PR paragraph: "The words were wrong because the model chose the wrong words"
“It was uhhhh, broken, but like, it’s totes fine now lol”
Unexpected responses from ChatGPT: Incident Report
101–110 of 277 posts
Re: Unexpected responses from ChatGPT: Incident Report
#102Is this the future of postmortems? "We tweaked a random seed, and it resulted in unfavorable random outcomes. "
Part of me believes that what went wrong would betray some "open" secret of theirs.
Re: Unexpected responses from ChatGPT: Incident Report
#103Earlier quoted context omitted.
What's even more uncanny is that it recognizes that it briefly went into a paragraph of rambling nonsense (that was seemingly still following your system prompt!). And almost seems embarrassed about it.
That happened because the last message is after the fix and it received the garbled history as the prompt. All it's doing is noticing that makes no sense and saying so. How could it not recognize it? The additional message is an entirely new instance not a thing that has memory.
>All it's doing is noticing that makes no sense and saying so. How could it not recognize it?
you say that like it's the simplest thing in the world. it really amazes me how quickly people acclimate to this mind-blowing tech.
Re: Unexpected responses from ChatGPT: Incident Report
#104This explanation feels unsatisfying. It's so high-level that it's mostly void of any actual information. What was the wrong assumption that the code made that caused this wrong behavior? Why was it not caught in the many layers of automated testing before it made its way to production? What process and procedural changes are being implemented to reduce the risk of this class of bug happening again? Presumably all of…
The explanation is definitely unsatisfying. If I had to guess it was an issue with quantization. OpenAI moves so quickly with their product and doesn't seem to be shy about quickly pushing changes to prod. There are too many times to count that, using ChatGPT, I've seen the frontend changing before my eyes or seen responses change as backend modifications are pushed. On one hand it's refreshing to see their lack of a…
Does the API offer "fixed" models that don't change? I was under the impression they did.
Re: Unexpected responses from ChatGPT: Incident Report
#105I am used to postmortems posted to here being a rare chance for us to take a peek behind the curtain and get a glimpse into things like architecture, monitoring systems, disaster recovery processes, "blameless culture", etc for large software service companies. In contrast, I feel like like the greatest insight that could be gleaned from this post is that OpenAI uses GPU's.
Someone posted an explanation that lines up with their postmortem: https://news.ycombinator.com/item?id=39450978
How does that line up? OpenAI said they had a bug in certain GPU configurations that caused the token numbers to be wrong which made normal output look like garbage. This post is guessing they set the frequency and presence penalties too high.
Re: Unexpected responses from ChatGPT: Incident Report
#106Earlier quoted context omitted.
That happened because the last message is after the fix and it received the garbled history as the prompt. All it's doing is noticing that makes no sense and saying so. How could it not recognize it? The additional message is an entirely new instance not a thing that has memory.
>All it's doing is noticing that makes no sense and saying so. How could it not recognize it? you say that like it's the simplest thing in the world. it really amazes me how quickly people acclimate to this mind-blowing tech.
I just mean, given that LLMs exist this isn't a surprising result. It only looks surprising because the UI makes you forget that each prompt is a completely new universe to the model.
Re: Unexpected responses from ChatGPT: Incident Report
#107I am used to postmortems posted to here being a rare chance for us to take a peek behind the curtain and get a glimpse into things like architecture, monitoring systems, disaster recovery processes, "blameless culture", etc for large software service companies. In contrast, I feel like like the greatest insight that could be gleaned from this post is that OpenAI uses GPU's.
ChatGPT had a stroke. Haven't seen that since the 3B parameter models from 8 months ago
Re: Unexpected responses from ChatGPT: Incident Report
#108Earlier quoted context omitted.
>All it's doing is noticing that makes no sense and saying so. How could it not recognize it? you say that like it's the simplest thing in the world. it really amazes me how quickly people acclimate to this mind-blowing tech.
I just mean, given that LLMs exist this isn't a surprising result. It only looks surprising because the UI makes you forget that each prompt is a completely new universe to the model.
I wouldn't call a step in a history-aware conversation a completely new universe. By that logic, every single time a token is generated is a new universe even though the token is largely dependent on the prompt, which includes custom instructions, chat history, and all tokens generated in the response so far.
Re: Unexpected responses from ChatGPT: Incident Report
#109I am used to postmortems posted to here being a rare chance for us to take a peek behind the curtain and get a glimpse into things like architecture, monitoring systems, disaster recovery processes, "blameless culture", etc for large software service companies. In contrast, I feel like like the greatest insight that could be gleaned from this post is that OpenAI uses GPU's.
We also know it uses the GPUs to generate numbers. But these numbers, they were the wrong ones. More technically, part of the computation didn’t work when run on some hardware.
Re: Unexpected responses from ChatGPT: Incident Report
#110Earlier quoted context omitted.
The point isn't the specifics; the point is that this isn't a postmortem. A postmortem should be detailed enough for someone to understand the background, how the problem came to be, then what happened, and the walk-through what has been done such that it won't happen again. It takes … well at least a page. This is far too short to quality. This is more "ugh, here's a rough explanation, please go away now" territory.…
Sorry, not disagreeing, just offering speculation in lieu of the answers we don't have.
That’s not helping, that’s excusing OpenAIs behavior, which is not something anyone on hn should be doing.
This is supposedly the greatest AI mankind has ever created, it goes down for a little while and we have zero information on why or how, that’s simply inexcusable
If this is such a socially impacting technical change we should be ripping it to pieces to understand exactly how it works. Thats a) how we protect society from technical charlatans b) how you spawn a whole new world of magnificent innovations (see Linus building a truly free Unix like operating system for everyone to use).
Failing to hold them to as high a bar is a another step down the path to a dystopian corporatists future…