Remix.run Logo
jonrouach a day ago

you're sure it's not their "feature" that calling the api with empty string returns random hallucinations?

https://jarbon.medium.com/gpt-prompt-bug-94322a96c574

requilence a day ago | parent [-]

No, definitely not the empty string hallucination bug. These are clearly real user conversations. They start like proper replies to requests, sometimes reference the original question, and appear in different languages.

jonrouach a day ago | parent | next [-]

i had the exact same behavior back in 2023, it seemed like clearly leakage of user conversations - but it was just a bug with api calls in the software i was using.

https://snipboard.io/FXOkdK.jpg

postalcoder a day ago | parent [-]

There was an issue with conversation leakage, though. It involved some bug with Redis.

I felt like it was a huge deal at the time but it’s surprisingly hard to quickly google it.

Sebguer a day ago | parent [-]

It was the classic "oh no we did caching wrong" bug that many startups bump into. It didn't expose actual conversations though, only their titles: https://openai.com/index/march-20-chatgpt-outage/

postalcoder a day ago | parent [-]

ah there it is. thanks for jogging my memory. funny to think of how niche chatgpt was considered then to now.

JyB a day ago | parent | prev | next [-]

I don’t see anything here that would prevent a LLM from generating these. Right?

requilence a day ago | parent [-]

In one of the responses, it provided the financial analysis of a not well-known company with a non-Latin name located in a small country. I found this company; it is real and numbers in the response are real. When I asked my ChatGPT to provide a financial report for this company without using web tools, it responded: `Unfortunately, I don’t have specific financial statements for “xxx” for 2021 and 2022 in my training data, and since you’ve asked not to use web search, I can’t pull them live.`.

BoiledCabbage 16 hours ago | parent | next [-]

> numbers in the response are real.

OpenAI very well may have a bug, but I'm not clear on this part. How do you know the numbers are real?

I understand you know the name is the company is real, but how do you know the numbers are real?

It's way may than anyone should need to do, but the only way I can see someone knowing this is contacting the owners is the company.

Sebguer a day ago | parent | prev [-]

Do you understand what a hallucination is?

jojobas a day ago | parent [-]

Coming up with accurate financial data that you can't get it to report outright doesn't seem like one.

Sebguer a day ago | parent | next [-]

Models do not possess awareness of their training data. Also you are taking at face value that it is "accurate".

refulgentis a day ago | parent | prev [-]

I don't understand the wording

Accurate financial data?

How do we know?

What does using not-web-search not having the data have to do with the claim that private chats with the data are being leaked?

01HNNWZ0MV43FF a day ago | parent [-]

> I found this company; it is real and numbers in the response are real.

???

refulgentis a day ago | parent [-]

Which of my questions does that answer?

queenkjuul a day ago | parent [-]

That the financial data is accurate?

refulgentis 16 hours ago | parent [-]

It's an ourobos - he can't verify it's real! If he can, its online and available by search.

JyB 7 hours ago | parent [-]

Therefore what are the odds that this is just the LLM doing its thing versus "a vulnerability". Seem like a pretty obvious bet.

addandsubtract 20 hours ago | parent | prev [-]

New Touring Test unlocked! Differentiate between real and fake hallucinations.

DANmode 10 hours ago | parent [-]

So THAT'S what the "GT" means on all of these GPU model names!