|
|
|
|
|
|
by qwerty3344
1189 days ago
|
|
|
using chatGPT to summarize: This section summarizes the issue with the ChatGPT service which caused some users to be able to see another user's chat history and payment information. OpenAI took the ChatGPT service offline and published technical details of the problem. The bug was found in the Redis client open-source library and has been patched. OpenAI has reached out to affected users and improved their systems to prevent this from happening again. They have also expressed their commitment to protecting user privacy and their dedication to the open-source community. |
|
|
> ChatGPT experienced an outage due to a bug in an open-source library that allowed some users to see titles from another active user's chat history and payment-related information of 1.2% of ChatGPT Plus subscribers was exposed; the bug has since been patched and actions have been taken to prevent future incidents.
I then asked it why there was the outage and it spit out:
> The exact cause of the Facebook outage is unknown, but it is believed to be related to a configuration change in the company's routers.
It's likely because I ran out of tokens because the OpenAI outage report is long. Pasting in the text of the outage report, and then re-asking about why, it was able to give a much better answer:
> There was an outage due to a bug in an open-source library that allowed some users to see titles from another active user's chat history and also unintentionally exposed payment-related information of 1.2% of ChatGPT Plus subscribers who were active during a specific nine-hour window.
Querying it further, again having to repeat the whole OpenAI outage report, and asking it a few different ways I eventually managed to get this succinct answer:
> The bug was caused by the redis-py library's shared pool of connections becoming corrupted and returning cached data belonging to another user when a request was cancelled before the corresponding response was received, due to a spike in Redis request cancellations caused by a server change on March 20.
It did take me more than a few minutes to get to there, so just actually reading the report would have been faster, and I ended up having to read the report to verify that answer was correct and not a hallucination anyway, so our jobs are safe for now.