Hacker News Reader

Comment by iraldir | Hacker News Reader

Mine says differently: https://chat.openai.com/share/792e3964-f96d-47c6-a598-b44791...

You cannot trust what it says about itself. As for knowing catastrophe, that's a pretty poor example as open ai as always it keeps the model up to date with major events (war in ukraine for instance).

View on HN

Did you try asking it the exact same question? - if you had, you would get something along the lines of:

I apologize for the inconvenience, but my data is current only up to January 2022, so I don't have information on catastrophes that may have occurred after that date. If you have any other questions or need information on events prior to 2022, feel free to ask.

it's a nondeterministic system... just because you ask it the same exact question doesn't mean you'll necessarily get the same response

It's a nondeterministic sensical system. Yes, sometimes it suffers from "hallucinations" (or whatever we're calling them these days). However, it's generally very good at regurgitating back it's limitations.

https://chat.openai.com/share/a18029ba-bf1b-4018-853f-206173...

https://chat.openai.com/share/49cd4e0d-9327-4984-8bba-1254b6...

How would you propose the person who linked the April 2023 chat log faked it? The way that the person phrased the question in the chat log was actually GREAT question to ask to show they indeed have an April 2023 version, as it's a particularly hard question to fake.

Suppose there is a partial rollout? There’s lots of possible explanations. I don’t think GP faked it, I’m pointing out a verbatim question/answer pair isn’t a reliable test.

Reply on news.ycombinator.com